Embodiments disclosed include methods and systems for signal processing using temporal neural networks integrated with state space models (SSMs). A computing system may receive radar signals, including in-phase and quadrature baseband samples, and extract features using an SSM that captures information associated with phase, frequency, amplitude, and signal structure. The system may generate a modified radar signal that includes temporal dependencies, downsample the modified radar signal to generate an intermediate representation, and provide the intermediate representation to a classifier to automatically identify a modulation type associated with the radar signal. Some embodiments include an SSM-based encoder-decoder architecture for real-time processing of audio signals including speech signals. The architecture may generate a denoised output signal for real-time enhancement of raw input signals on edge devices with reduced latency and memory requirements.
G01S 7/41 - Details of systems according to groups , , of systems according to group using analysis of echo signal for target characterisationTarget signatureTarget cross-section
Embodiments disclosed include methods and systems for signal processing using temporal neural networks integrated with state space models (SSMs). A computing system may receive radar signals, including in-phase and quadrature baseband samples, and extract features using an SSM that captures information associated with phase, frequency, amplitude, and signal structure. The system may generate a modified radar signal that includes temporal dependencies, downsample the modified radar signal to generate an intermediate representation, and provide the intermediate representation to a classifier to automatically identify a modulation type associated with the radar signal. Some embodiments include an SSM-based encoder-decoder architecture for real-time processing of audio signals including speech signals. The architecture may generate a denoised output signal for real-time enhancement of raw input signals on edge devices with reduced latency and memory requirements.
G01S 7/41 - Details of systems according to groups , , of systems according to group using analysis of echo signal for target characterisationTarget signatureTarget cross-section
42 - Scientific, technological and industrial services, research and design
Goods & Services
Research, consulting and design services concerning the development of computer software programs and architecture and computer hardware architecture; research, consulting and design services in the field of developing computer software for artificial intelligence, neural networks; computer network configuration services, namely, configuration of neuromorphic systems, neuromorphic computations and artificial neural networks; technical support services, namely, troubleshooting in the nature of diagnosing computer hardware and computer software problems; integration of computer hardware and software being computer services, namely, integration of computer software into computer hardware systems; computer software and hardware testing services; installation, updating and maintenance of computer software; computer programming services for others; providing online non-downloadable software for using artificial intelligence computer chips to design software applications; providing online non-downloadable software for neuromorphic computing; providing online non-downloadable software for building artificial intelligence platforms; providing online non-downloadable software for machine learning, cognitive computing, deep learning and for designing software applications using artificial intelligence; providing online non-downloadable application programming interface (API) software; providing online non-downloadable software in the nature of a widget for machine learning and for designing software applications using artificial intelligence; software as a service (SAAS) services featuring software for use in software development of applications and interfaces for developers; customization of web software, namely, application programming interface design for others; Providing online non-downloadable computer software for information processing in which information is processed in a manner similar to the way the human brain processes information
09 - Scientific and electric apparatus and instruments
Goods & Services
Electronic data processing apparatus; computer chips; computer chip sets; microchips; neuromorphic computer chips; semiconductor processor chips; computer hardware to enable artificial intelligence applications; computer hardware to enable neuromorphic computation; neural network processors being central processing units; neuromorphic data processors; integrated circuits; computers chips having a predefined architecture; downloadable computer software and computer hardware for information processing in which information is processed in a manner similar to the way the human brain processes information; downloadable computer software for designing and developing software applications; downloadable computer software application programs which implement software interfaces for designing and developing artificial intelligence software; electronic data processing apparatus for the delivery of an artificial intelligence platform based on neuromorphic computation; downloadable software for using artificial intelligence computer chips to design software applications; downloadable software for neuromorphic computing; downloadable software for building artificial intelligence platforms and artificial intelligence platforms based on neuromorphic computation; downloadable software for machine learning, cognitive computing, deep learning, and for designing software applications using artificial intelligence; downloadable application programming interface (API) software; downloadable software in the nature of a widget for machine learning and for designing software applications using artificial intelligence
5.
METHODS AND DEVICES FOR AUTHENTICATING INDIVIDUALS BASED ON DYNAMIC FACIAL EXPRESSIONS AND DEVICE MOTION
Various embodiments provide a secure biometric authentication method using dynamic facial expression gestures and motion. A mobile device captures spatiotemporal data of a user's facial features via a vision sensor and motion data associated with a mobile device's movement via an inertial measurement unit (IMU). A processing system in the mobile device constructs composite spatiotemporal trajectories of facial features by combining the event-based data and motion data, which are then matched to a stored template of biometric gestures associated with an authorized user. A neural network may be used to process these trajectories to determine the dynamic facial features and mobile device movements that correspond to an authorized user. If so, the mobile device may provide access to protected assets or secure operations of a device or to protected files. This dual-layer security approach enhances protection against unauthorized access by requiring precise replication of both facial dynamics and device motion.
Systems and methods performed by a processor of a computing device for implementing a plurality of state space models (SSM) by a processing system. Embodiments may include receiving a data input at a driving SSM, generating a driving output of the driving SSM based on the data input, parameterizing a driven SSM based on the driving output, in which the driving SSM and the driven SSM are connected by a lateral connection, receiving a second data input at the driven SSM, and generating a driven output of the driven SSM based on parameterization of the driven SSM and the second data input.
Various embodiments provide a secure biometric authentication method using dynamic facial expression gestures and motion. A mobile device captures spatiotemporal data of a user's facial features via a vision sensor and motion data associated with a mobile device's movement via an inertial measurement unit (IMU). A processing system in the mobile device constructs composite spatiotemporal trajectories of facial features by combining the event-based data and motion data, which are then matched to a stored template of biometric gestures associated with an authorized user. A neural network may be used to process these trajectories to determine the dynamic facial features and mobile device movements that correspond to an authorized user. If so, the mobile device may provide access to protected assets or secure operations of a device or to protected files. This dual-layer security approach enhances protection against unauthorized access by requiring precise replication of both facial dynamics and device motion.
G06F 21/32 - User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
G06F 21/35 - User authentication involving the use of external additional devices, e.g. dongles or smart cards communicating wirelessly
G06V 10/147 - Details of sensors, e.g. sensor lenses
G06V 10/24 - Aligning, centring, orientation detection or correction of the image
G06V 10/74 - Image or video pattern matchingProximity measures in feature spaces
G06V 10/75 - Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video featuresCoarse-fine approaches, e.g. multi-scale approachesImage or video pattern matchingProximity measures in feature spaces using context analysisSelection of dictionaries
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 40/16 - Human faces, e.g. facial parts, sketches or expressions
G06V 40/40 - Spoof detection, e.g. liveness detection
G06V 40/70 - Multimodal biometrics, e.g. combining information from different biometric modalities
8.
System of Interconnected State Space Models with Jointly Driven State Matrices
Systems and methods performed by a processor of a computing device for implementing a plurality of state space models (SSM) by a processing system. Embodiments may include receiving a data input at a driving SSM, generating a driving output of the driving SSM based on the data input, parameterizing a driven SSM based on the driving output, in which the driving SSM and the driven SSM are connected by a lateral connection, receiving a second data input at the driven SSM, and generating a driven output of the driven SSM based on parameterization of the driven SSM and the second data input.
Systems and methods performed by a processor of a computing device for online audio enhancement. Embodiments may include encoding an input audio signal by an encoder of a deep state-space autoencoder based in part on executing a first state-space model (SSM) generating an encoded signal, decoding a signal derived in part from the encoded signal by a decoder of the deep state-space autoencoder based in part on executing a second SSM to generate a decoded signal, and generating an enhanced output signal based in part on executing a third SSM based on the decoded signal.
G10L 25/30 - Speech or voice analysis techniques not restricted to a single one of groups characterised by the analysis technique using neural networks
10.
SYSTEM AND METHOD FOR EFFICIENT EXECUTION OF LARGE GENERATIVE ARTIFICIAL INTELLIGENCE MODELS ON EDGE DEVICES USING STATE-SPACE MODELS
Systems and methods for multi‑source hidden‑state fusion on edge devices. A processing system executes a state‑space model, accesses a vector database in dynamic random‑access memory, and maintains model state in on‑chip static random‑access memory. The system processes document chunks to form hidden states and computes a key for each chunk. Tuples pairing each key with a hidden state are stored in the database. For a received query, the system computes a query key and retrieves tuples by nearest‑neighbor search using the stored keys and the query key. A fusion function computes a fused hidden state across the retrieved hidden states. The fused hidden state is loaded as the initialization state. The model processes the query tokens from that state and generates answer tokens as a function of the fused state and the query tokens.
Systems and methods for multi-source hidden-state fusion on edge devices. A processing system executes a state-space model, accesses a vector database in dynamic random-access memory, and maintains model state in on-chip static random-access memory. The system processes document chunks to form hidden states and computes a key for each chunk. Tuples pairing each key with a hidden state are stored in the database. For a received query, the system computes a query key and retrieves tuples by nearest-neighbor search using the stored keys and the query key. A fusion function computes a fused hidden state across the retrieved hidden states. The fused hidden state is loaded as the initialization state. The model processes the query tokens from that state and generates answer tokens as a function of the fused state and the query tokens.
Disclosed is a neural network system generally relates to the field of neural networks (NNs). In particular, the present disclosure relates to event-based convolutional neural networks (NNs) that are trained to process spatial and temporal data using kernels represented by polynomial expansion. The event-based convolutional neural networks (NNs) are spatiotemporal neural networks. According to an embodiment, an explicit temporal convolution capability is added through Temporal Event-based Neural Networks (TENN) models. or TENNs in the spatiotemporal neural networks. The TENNs includes a plurality of temporal and spatial convolution layers that combine spatial and temporal features of data for low-level and high-level features. The TENNs as disclosed herein are configured to perform in a buffer mode and recurrent mode that effectively learns both spatial and temporal correlations from the input data.
Disclosed is a method for processing event-based input data using a neural network. The neural network comprises a plurality of neurons and one or more connections associated with each of the plurality of neurons. Further, each of the plurality of neurons is configured to receive a corresponding portion of the event-based data. The method comprises receiving, at a neuron of the plurality of neurons, a plurality of events associated with the event-based data over the one or more connections associated with the neuron. Each of the one or more connections is associated with a kernel. The method further comprises determining a potential of the neuron over the period of time based on processing of the kernels. In order to determine the potential, the method further comprises offsetting the kernels in one of a spatial dimension, a temporal dimension, or a spatiotemporal dimension, and processing the offset kernels in order to determine the potential. The method further comprises generating, at the neuron, output based on the determined potential.
Disclosed is a neural network system that includes a memory and a processor. The memory is configured to store a plurality of storage buffers corresponding to a current neural network layer, and implement a neural network that includes a plurality of neurons for the current neural network layer and a corresponding group among a plurality of groups of basis function values. The processor is configured to receive an input data sequence into the first plurality of storage buffers over a first time sequence and project the input data sequence on a corresponding basis function values by performing, for each connection of a corresponding neuron, a dot product of the first input data sequence within a corresponding storage buffer with the corresponding basis function values and thereby determine a corresponding potential value for the corresponding neurons. Thus, utilizing the corresponding potential values, the processor generates a plurality of encoded output responses.
Disclosed is a neural network system that includes a memory and a processor. The memory is configured to store a plurality of storage buffers corresponding to a current neural network layer, and implement a neural network that includes a plurality of neurons for the current neural network layer and a corresponding group among a plurality of groups of basis function values. The processor is configured to receive an input data sequence into the first plurality of storage buffers over a first time sequence and project the input data sequence on a corresponding basis function values by performing, for each connection of a corresponding neuron, a dot product of the first input data sequence within a corresponding storage buffer with the corresponding basis function values and thereby determine a corresponding potential value for the corresponding neurons. Thus, utilizing the corresponding potential values, the processor generates a plurality of encoded output responses.
Disclosed is a system that includes a processor configured to process data in a neural network and a memory associated with a primary flow path and at least one secondary flow path within the neural network. The primary flow path comprises one or more primary operators to process the data and the at least one secondary flow path is configured to pass the data to a combining operator by skipping the processing of the data over the primary flow path. The processor is configured to provide the primary flow path and the at least one secondary flow path with a primary sequence of data and a secondary sequence of data respectively such that the secondary sequence of data being time offset from the processed primary sequence of data.
Disclosed is a method for processing event-based input data using a neural network. The neural network comprises a plurality of neurons and one or more connections associated with each of the plurality of neurons. Further, each of the plurality of neurons is configured to receive a corresponding portion of the event-based data. The method comprises receiving, at a neuron of the plurality of neurons, a plurality of events associated with the event-based data over the one or more connections associated with the neuron. Each of the one or more connections is associated with a kernel. The method further comprises determining a potential of the neuron over the period of time based on processing of the kernels. In order to determine the potential, the method further comprises offsetting the kernels in one of a spatial dimension, a temporal dimension, or a spatiotemporal dimension, and processing the offset kernels in order to determine the potential. The method further comprises generating, at the neuron, output based on the determined potential.
Disclosed is a neural network system generally relates to the field of neural networks (NNs). In particular, the present disclosure relates to event-based convolutional neural networks (NNs) that are trained to process spatial and temporal data using kernels represented by polynomial expansion. The event-based convolutional neural networks (NNs) are spatiotemporal neural networks. According to an embodiment, an explicit temporal convolution capability is added through Temporal Event-based Neural Networks (TENN) models, or TENNs in the spatiotemporal neural networks. The TENNs includes a plurality of temporal and spatial convolution layers that combine spatial and temporal features of data for low-level and high-level features. The TENNs as disclosed herein are configured to perform in a buffer mode and recurrent mode that effectively learns both spatial and temporal correlations from the input data.
A system is described that comprises a memory for storing data representative of at least one kernel, a plurality of spiking neuron circuits, and an input module for receiving spikes related to digital data. Each spike is relevant to a spiking neuron circuit and each spike has an associated spatial coordinate corresponding to a location in an input spike array. The system also comprises a packet collection module configured to collect spikes and to organize the collected relevant spikes in the packet based on the spatial coordinates of the spikes, and a convolutional neural processor configured to perform event-based convolution using memory and at least one of the transformed input spike array and the transformed kernel.
G06F 15/18 - in which a program is changed according to experience gained by the computer itself during a complete run; Learning machines (adaptive control systems G05B 13/00;artificial intelligence G06N)
G06G 7/00 - Devices in which the computing operation is performed by varying electric or magnetic quantities
G06K 9/00 - Methods or arrangements for reading or recognising printed or written characters or for recognising patterns, e.g. fingerprints
Disclosed herein are system, method, and computer program embodiments for an improved spiking neural network (SNN) configured to learn and perform unsupervised, semi-supervised, and supervised extraction of features from an input dataset. An embodiment operates by receiving a modification request to modify a base neural network, having N layers and a plurality of spiking neurons, trained using a primary training dataset. The base neural network is modified to include supplementary spiking neurons in the Nth or N+1th layer of the base neural network. The embodiment includes receiving a secondary training dataset and determining membrane potential values of one or more supplementary spiking neurons in the Nth or Nth+1 layer which learn features based on secondary training data set to select a supplementary/winning spiking neuron. The embodiment performs a learning function for the modified neural network based on the winning spiking neuron.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Electronic data processing apparatus; computer chips; computer chip sets primarily comprised of computer chips; microchips; neuromorphic computer chips; semiconductor processor chips; computer hardware to enable artificial intelligence applications; computer hardware to enable neuromorphic computation; neural network processors; neuromorphic data processors; integrated circuits; computers chips having a predefined architecture; downloadable computer software and hardware for information processing in which information is processed in a manner similar to the way the human brain processes information; downloadable computer software for designing and developing software applications; downloadable computer software application programs which implement software interfaces for designing and developing artificial intelligence software; electronic data processing apparatus for the delivery of an artificial intelligence platform based on neuromorphic computation; downloadable software for use in the operation of artificial intelligence computer chips; downloadable software for neuromorphic computing for creating new software programs; downloadable software for building artificial intelligence platforms and artificial intelligence platforms based on neuromorphic computation; downloadable electronic data files featuring microprocessor designs; downloadable electronic data files featuring microprocessor designs to implement neural network; downloadable electronic data files featuring microprocessor designs to implement temporal convolution; downloadable software for machine learning, cognitive computing, deep learning, artificial intelligence, all for creating new software programs; downloadable application programming interface (API) software; downloadable software for machine learning and for using artificial intelligence to communicate with other computers Research, consulting and design services concerning the development of computer software programs and architecture and computer hardware architecture; research, consulting and design services in the field of developing computer software for artificial intelligence, neural networks; computer network configuration services, namely, configuration of neuromorphic systems, neuromorphic computations and artificial neural networks; research, development and design for use in the design, technical verification and development of neural network processors for others; integration of computer hardware and software being computer services, namely, integration of computer software into computer hardware systems; computer software and hardware testing services; installation, updating and maintenance of computer software; computer programming services for others; providing online non-downloadable software for using artificial intelligence computer chips to design software applications; providing online non-downloadable software for neuromorphic computing for creating new software programs; providing online non-downloadable software for building artificial intelligence platforms; providing online non-downloadable software for machine learning, cognitive computing, deep learning, all for creating new software programs and for designing software applications using artificial intelligence; providing online non-downloadable application programming interface (API) software; providing online non-downloadable software for machine learning and for using artificial intelligence to communicate with other computers; software as a service (SAAS) services featuring software for use in software development of applications and interfaces for developers; customization of web software, namely, application programming interface design for others; providing online non-downloadable computer software for information processing in which information is processed in a manner similar to the way the human brain processes information; technical consultancy and technical support services in the nature of diagnosing problems with processors, namely, neural network processor
Disclosed herein are system, method, and computer program product embodiments for an improved spiking neural network (SNN) configured to learn and perform unsupervised extraction of features from an input stream. An embodiment operates by receiving a set of spike bits corresponding to a set synapses associated with a spiking neuron circuit. The embodiment applies a first logical AND function to a first spike bit in the set of spike bits and a first synaptic weight of a first synapse in the set of synapses. The embodiment increments a membrane potential value associated with the spiking neuron circuit based on the applying. The embodiment determines that the membrane potential value associated with the spiking neuron circuit reached a learning threshold value. The embodiment then performs a Spike Time Dependent Plasticity (STDP) learning function based on the determination that the membrane potential value of the spiking neuron circuit reached the learning threshold value.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Electronic data processing apparatus; computer chips;
computer chip sets; microchips; neuromorphic computer chips;
semiconductor processor chips; computer hardware to enable
artificial intelligence applications; computer hardware to
enable neuromorphic computation; neural network processors
being central processing units; neuromorphic data
processors; integrated circuits; computers chips having a
predefined architecture; downloadable computer software and
computer hardware for information processing in which
information is processed in a manner similar to the way the
human brain processes information; downloadable computer
software for designing and developing software applications;
downloadable computer software application programs which
implement software interfaces for designing and developing
artificial intelligence software; electronic data processing
apparatus for the delivery of an artificial intelligence
platform based on neuromorphic computation; downloadable
software for using artificial intelligence computer chips to
design software applications; downloadable software for
neuromorphic computing; downloadable software for building
artificial intelligence platforms and artificial
intelligence platforms based on neuromorphic computation;
downloadable software for machine learning, cognitive
computing, deep learning, and for designing software
applications using artificial intelligence; downloadable
application programming interface (API) software;
downloadable software in the nature of a widget for machine
learning and for designing software applications using
artificial intelligence. Research, consulting and design services concerning the
development of computer software programs and architecture
and computer hardware architecture; research, consulting and
design services in the field of developing computer software
for artificial intelligence, neural networks; computer
network configuration services, namely, configuration of
neuromorphic systems, neuromorphic computations and
artificial neural networks; technical support services,
namely, troubleshooting in the nature of diagnosing computer
hardware and computer software problems; integration of
computer hardware and software being computer services,
namely, integration of computer software into computer
hardware systems; computer software and hardware testing
services; installation, updating and maintenance of computer
software; computer programming services for others;
providing online non-downloadable software for using
artificial intelligence computer chips to design software
applications; providing online non-downloadable software for
neuromorphic computing; providing online non-downloadable
software for building artificial intelligence platforms;
providing online non-downloadable software for machine
learning, cognitive computing, deep learning and for
designing software applications using artificial
intelligence; providing online non-downloadable application
programming interface (API) software; providing online
non-downloadable software in the nature of a widget for
machine learning and for designing software applications
using artificial intelligence; software as a service (SAAS)
services featuring software for use in software development
of applications and interfaces for developers; customization
of web software, namely, application programming interface
design for others; providing online non-downloadable
computer software for information processing in which
information is processed in a manner similar to the way the
human brain processes information.
09 - Scientific and electric apparatus and instruments
Goods & Services
Electronic data processing apparatus; computer chips;
computer chip sets; microchips; neuromorphic computer chips;
semiconductor processor chips; computer hardware to enable
artificial intelligence applications; computer hardware to
enable neuromorphic computation; neural network processors;
neuromorphic data processors; integrated circuits; computer
chips having a predefined architecture; computer software
and hardware for information processing in which information
is processed in a manner similar to the way the human brain
processes information; downloadable computer software for
designing and developing software applications; downloadable
computer software application programs which implement
software interfaces for designing and developing artificial
intelligence software; electronic data processing apparatus
for the delivery of an artificial intelligence platform
based on neuromorphic computation; downloadable software for
using artificial intelligence computer chips; downloadable
software for neuromorphic computing; downloadable software
for building artificial intelligence platforms and
artificial intelligence platforms based on neuromorphic
computation; downloadable software for machine learning,
cognitive computing, deep learning, artificial intelligence;
downloadable application programming interface (API)
software; downloadable software in the nature of a widget
for machine learning and artificial intelligence.
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Electronic data processing apparatus; computer chips;
computer chip sets; microchips; neuromorphic computer chips;
semiconductor processor chips; computer hardware to enable
artificial intelligence applications; computer hardware to
enable neuromorphic computation; neural network processors;
neuromorphic data processors; integrated circuits; computers
chips having a predefined architecture; computer software
and hardware for information processing in which information
is processed in a manner similar to the way the human brain
processes information; downloadable computer software for
designing and developing software applications; downloadable
computer software application programs which implement
software interfaces for designing and developing artificial
intelligence software; electronic data processing apparatus
for the delivery of an artificial intelligence platform
based on neuromorphic computation; downloadable software for
using artificial intelligence computer chips; downloadable
software for neuromorphic computing; downloadable software
for building artificial intelligence platforms and
artificial intelligence platforms based on neuromorphic
computation; downloadable software for machine learning,
cognitive computing, deep learning, artificial intelligence;
downloadable application programming interface (API)
software; downloadable software in the nature of a widget
for machine learning and artificial intelligence. Research, consulting and design services concerning the
development of computer software programs and architecture
and computer hardware architecture; research, consulting and
design services in the field of developing computer software
for artificial intelligence, neural networks; computer
network configuration services, namely, configuration of
neuromorphic systems, neuromorphic computations and
artificial neural networks; integration of computer hardware
and software being computer services, namely, integration of
computer software into computer hardware systems; computer
software and hardware testing services; installation,
updating and maintenance of computer software; computer
programming services for others; providing online
non-downloadable software for using artificial intelligence
computer chips to design software applications; providing
online non-downloadable software for neuromorphic computing;
providing online non-downloadable software for building
artificial intelligence platforms; providing online
non-downloadable software for machine learning, cognitive
computing, deep learning and for designing software
applications using artificial intelligence; providing online
non-downloadable application programming interface (API)
software; providing online non-downloadable software in the
nature of a widget for machine learning and for designing
software applications using artificial intelligence;
software as a service (SAAS) services featuring software for
use in software development of applications and interfaces
for developers; customization of web software, namely,
application programming interface design for others;
providing online non-downloadable computer software for
information processing in which information is processed in
a manner similar to the way the human brain processes
information.
42 - Scientific, technological and industrial services, research and design
Goods & Services
Research, consulting and design services in the field of
developing computer software, namely, artificial
intelligence, neural networks; neuromorphic systems,
neuromorphic computations and artificial neural networks
related software; technical support services, namely,
troubleshooting of computer software problems; computer
programming services for others; non-downloadable software
in the nature of a widget for machine learning and
artificial intelligence; software as a service services
featuring software for applications and interfaces for
developers, namely, for the control and configuration of
neuromorphic processor for artificial intelligence
applications, and its associated user interface software;
customization of web software, namely, application
programming interface design for others.
09 - Scientific and electric apparatus and instruments
37 - Construction and mining; installation and repair services
42 - Scientific, technological and industrial services, research and design
Goods & Services
Electronic data processing apparatus; computer chips; computer chip sets; microchips; neuromorphic computer chips; semiconductor processor chips; computer hardware to enable artificial intelligence applications; computer hardware to enable neuromorphic computation; neural network processors being central processing units; neuromorphic data processors; integrated circuits; computers chips having a predefined architecture; downloadable computer software and computer hardware for information processing in which information is processed in a manner similar to the way the human brain processes information; downloadable computer software for designing and developing software applications; downloadable computer software application programs which implement software interfaces for designing and developing artificial intelligence software; electronic data processing apparatus for the delivery of an artificial intelligence platform based on neuromorphic computation; downloadable software for using artificial intelligence computer chips to design software applications; downloadable software for neuromorphic computing; downloadable software for building artificial intelligence platforms and artificial intelligence platforms based on neuromorphic computation; downloadable software for machine learning, cognitive computing, deep learning, and for designing software applications using artificial intelligence; downloadable application programming interface (API) software; downloadable software in the nature of a widget for machine learning and for designing software applications using artificial intelligence Technical support services, namely, troubleshooting in the nature of repair of computer hardware problems; customization of computer hardware; consultancy relating to the repair of computer processors; providing information and consultancy in the field of repair of neuromorphic computer processors Research, consulting and design services concerning the development of computer software programs and architecture and computer hardware architecture; research, consulting and design services in the field of developing computer software for artificial intelligence, neural networks; computer network configuration services, namely, configuration of neuromorphic systems, neuromorphic computations and artificial neural networks; technical support services, namely, troubleshooting in the nature of diagnosing computer hardware and computer software problems; integration of computer hardware and software being computer services, namely, integration of computer software into computer hardware systems; computer software and hardware testing services; installation, updating and maintenance of computer software; computer programming services for others; providing online non-downloadable software for using artificial intelligence computer chips to design software applications; providing online non-downloadable software for neuromorphic computing; providing online non-downloadable software for building artificial intelligence platforms; providing online non-downloadable software for machine learning, cognitive computing, deep learning and for designing software applications using artificial intelligence; providing online non-downloadable application programming interface (API) software; providing online non-downloadable software in the nature of a widget for machine learning and for designing software applications using artificial intelligence; software as a service (SAAS) services featuring software for use in software development of applications and interfaces for developers; customization of web software, namely, application programming interface design for others; Providing online non-downloadable computer software for information processing in which information is processed in a manner similar to the way the human brain processes information; compilation of information relating to information technology for technology research purposes; compilation of statistical data for information technology research purposes; computer technology consultancy relating to computer processors; providing information and consultancy in the field of computer technology relating to neuromorphic computer processors; research in the field of computer processors
09 - Scientific and electric apparatus and instruments
35 - Advertising and business services
37 - Construction and mining; installation and repair services
42 - Scientific, technological and industrial services, research and design
Goods & Services
Electronic data processing apparatus; computer chips; computer chip sets; microchips; neuromorphic computer chips; semiconductor processor chips; computer hardware to enable artificial intelligence applications; computer hardware to enable neuromorphic computation; neural network processors being central processing units; neuromorphic data processors; integrated circuits; computers chips having a predefined architecture; downloadable computer software and computer hardware for information processing in which information is processed in a manner similar to the way the human brain processes information; downloadable computer software for designing and developing software applications; downloadable computer software application programs which implement software interfaces for designing and developing artificial intelligence software; electronic data processing apparatus for the delivery of an artificial intelligence platform based on neuromorphic computation; downloadable software for using artificial intelligence computer chips to design software applications; downloadable software for neuromorphic computing; downloadable software for building artificial intelligence platforms and artificial intelligence platforms based on neuromorphic computation; downloadable software for machine learning, cognitive computing, deep learning, and for designing software applications using artificial intelligence; downloadable application programming interface (API) software; downloadable software in the nature of a widget for machine learning and for designing software applications using artificial intelligence Compilation of information into computer databases; compilation of information relating to information technology for business purposes; compilation of statistical data for business purposes; computerised data processing; computerised database management; consultancy for providing purchasing advice to consumers relating to the selection and purchase of computer processors; information and consultancy in the field of providing consumer information and advice about the selection and purchase of neuromorphic computer processors; data processing; electronic data processing; online data processing services Technical support services, namely, troubleshooting in the nature of repair of computer hardware problems; customization of computer hardware; consultancy relating to the repair of computer processors; providing information and consultancy in the field of repair of neuromorphic computer processors Research, consulting and design services concerning the development of computer software programs and architecture and computer hardware architecture; research, consulting and design services in the field of developing computer software for artificial intelligence, neural networks; computer network configuration services, namely, configuration of neuromorphic systems, neuromorphic computations and artificial neural networks; technical support services, namely, troubleshooting in the nature of diagnosing computer hardware and computer software problems; integration of computer hardware and software being computer services, namely, integration of computer software into computer hardware systems; computer software and hardware testing services; installation, updating and maintenance of computer software; computer programming services for others; providing online non-downloadable software for using artificial intelligence computer chips to design software applications; providing online non-downloadable software for neuromorphic computing; providing online non-downloadable software for building artificial intelligence platforms; providing online non-downloadable software for machine learning, cognitive computing, deep learning and for designing software applications using artificial intelligence; providing online non-downloadable application programming interface (API) software; providing online non-downloadable software in the nature of a widget for machine learning and for designing software applications using artificial intelligence; software as a service (SAAS) services featuring software for use in software development of applications and interfaces for developers; customization of web software, namely, application programming interface design for others; Providing online non-downloadable computer software for information processing in which information is processed in a manner similar to the way the human brain processes information; compilation of information relating to information technology for technology research purposes; compilation of statistical data for information technology research purposes; computer technology consultancy relating to computer processors; providing information and consultancy in the field of computer technology relating to neuromorphic computer processors; research in the field of computer processors
29.
Event-based extraction of features in a convolutional spiking neural network
A system is described that comprises a memory for storing data representative of at least one kernel, a plurality of spiking neuron circuits, and an input module for receiving spikes related to digital data. Each spike is relevant to a spiking neuron circuit and each spike has an associated spatial coordinate corresponding to a location in an input spike array. The system also comprises a transformation module configured to transform a kernel to produce a transformed kernel having an increased resolution relative to the kernel, and/or transform the input spike array to produce a transformed input spike array having an increased resolution relative to the input spike array. The system also comprises a packet collection module configured to collect spikes until a predetermined number of spikes relevant to the input spike array have been collected in a packet in memory, and to organize the collected relevant spikes in the packet based on the spatial coordinates of the spikes, and a convolutional neural processor configured to perform event-based convolution using memory and at least one of the transformed input spike array and the transformed kernel.
G06T 3/40 - Scaling of whole images or parts thereof, e.g. expanding or contracting
G06T 3/4046 - Scaling of whole images or parts thereof, e.g. expanding or contracting using neural networks
G11C 11/41 - Digital stores characterised by the use of particular electric or magnetic storage elementsStorage elements therefor using electric elements using semiconductor devices using transistors forming cells with positive feedback, i.e. cells not needing refreshing or charge regeneration, e.g. bistable multivibrator or Schmitt trigger
G11C 11/54 - Digital stores characterised by the use of particular electric or magnetic storage elementsStorage elements therefor using elements simulating biological cells, e.g. neuron
30.
Event-based classification of features in a reconfigurable and temporally coded convolutional spiking neural network
Embodiments of the present invention provides a system and method of learning and classifying features to identify objects in images using a temporally coded deep spiking neural network, a classifying method by using a reconfigurable spiking neural network device or software comprising configuration logic, a plurality of reconfigurable spiking neurons and a second plurality of synapses. The spiking neural network device or software further comprises a plurality of user-selectable convolution and pooling engines. Each fully connected and convolution engine is capable of learning features, thus producing a plurality of feature map layers corresponding to a plurality of regions respectively, each of the convolution engines being used for obtaining a response of a neuron in the corresponding region. The neurons are modeled as Integrate and Fire neurons with a non-linear time constant, forming individual integrating threshold units with a spike output, eliminating the need for multiplication and addition of floating-point numbers.
G06N 3/063 - Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using electronic means
G11C 11/41 - Digital stores characterised by the use of particular electric or magnetic storage elementsStorage elements therefor using electric elements using semiconductor devices using transistors forming cells with positive feedback, i.e. cells not needing refreshing or charge regeneration, e.g. bistable multivibrator or Schmitt trigger
G11C 11/54 - Digital stores characterised by the use of particular electric or magnetic storage elementsStorage elements therefor using elements simulating biological cells, e.g. neuron
09 - Scientific and electric apparatus and instruments
Goods & Services
Electronic data processing apparatus; computer chips;
computer chip sets; microchips; neuromorphic computer chips;
semiconductor processor chips; computer hardware to enable
artificial intelligence applications; computer hardware to
enable neuromorphic computation; neural network processors;
neuromorphic data processors; integrated circuits; computer
chips having a predefined architecture; computer software
and hardware for information processing in which information
is processed in a manner similar to the way the human brain
processes information; downloadable computer software for
designing and developing software applications; downloadable
computer software application programs which implement
software interfaces for designing and developing artificial
intelligence software; electronic data processing apparatus
for the delivery of an artificial intelligence platform
based on neuromorphic computation; downloadable software for
using artificial intelligence computer chips; downloadable
software for neuromorphic computing; downloadable software
for building artificial intelligence platforms and
artificial intelligence platforms based on neuromorphic
computation; downloadable software for machine learning,
cognitive computing, deep learning, artificial intelligence;
downloadable application programming interface (API)
software; downloadable software in the nature of a widget
for machine learning and artificial intelligence.
09 - Scientific and electric apparatus and instruments
Goods & Services
(1) Electronic data processing apparatus namely computers; computer chips; integrated circuit computer chip sets; microchips; neuromorphic computer chips; semiconductor processor chips; computer hardware to enable artificial intelligence applications; computer hardware to enable neuromorphic computation; neural network processors; neuromorphic data processors; integrated circuits; computers chips having a predefined architecture; computer software for neuromorphic computing, namely software based on the structures, processes and capacities of biological brains for creating artificial neural networks; downloadable computer software development kits for designing and developing software applications in the fields of machine learning, cognitive computing, deep learning, artificial intelligence; downloadable computer software application programs which implement software interfaces for designing and developing artificial intelligence software; downloadable computer software for the delivery of an artificial intelligence platform based on neuromorphic computation; downloadable software for use with artificial intelligence computer chips for designing and developing artificial intelligence computer systems; downloadable software for neuromorphic computing; downloadable software for building artificial intelligence platforms and artificial intelligence platforms based on neuromorphic computation; downloadable software developments kits for machine learning, cognitive computing, deep learning, artificial intelligence; downloadable application programming interface (API) software for analyzing clinical data for scientific and medical research; downloadable software in the nature of a software widget for machine learning and for designing software applications using artificial intelligence;
42 - Scientific, technological and industrial services, research and design
Goods & Services
(1) Research, consulting and design services in the field of developing computer software, namely, artificial intelligence, neural networks, neuromorphic computing, neuromorphic computations namely algorithmic approaches which emulate biological brain functions and software based on the structures, processes and capacities of biological brains to create artificial neural networks; technical support services, namely, troubleshooting of computer software problems; computer programming services for others; non-downloadable software widget for machine learning and for designing software applications using artificial intelligence; software as a service (SAAS) services featuring software for applications and interfaces for developers, namely, for the control and configuration of neuromorphic processor for Artificial Intelligence applications, and its associated user interface software; customization of web software, namely, application programming interface design for others;
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
(1) Electronic data processing apparatus namely computers; computer hardware to enable artificial intelligence applications; computer hardware to enable neuromorphic computation; computer software for neuromorphic computing, namely software for replicating the processing of information in a manner which emulates biological human brain functions; downloadable computer software development kits for designing and developing software applications in the fields of machine learning, cognitive computing, deep learning, artificial intelligence; downloadable computer software application programs which implement software interfaces for designing and developing artificial intelligence software; downloadable computer software for the delivery of an artificial intelligence platform based on neuromorphic computation; downloadable software for neuromorphic computing; downloadable software for building artificial intelligence platforms and artificial intelligence platforms based on neuromorphic computation; downloadable software developments kits for machine learning, cognitive computing, deep learning, artificial intelligence; downloadable application programming interface (API) software for analyzing clinical data for scientific and medical research; downloadable software widget for machine learning and for designing software applications using artificial intelligence; (1) Research, consulting and design services concerning the development of computer software programs and architecture and computer hardware architecture; research, consulting and design services in the field of developing computer software for artificial intelligence, neural networks; computer network configuration services, namely, configuration of neuromorphic systems, neuromorphic computations and artificial neural networks; integration of computer hardware and software being computer services, namely, integration of computer software into computer hardware systems; computer software and hardware testing services; installation, updating and maintenance of computer software; computer programming services for others; providing online non-downloadable software for neuromorphic computing; providing online non-downloadable software for building artificial intelligence platforms; providing online non-downloadable software for machine learning, cognitive computing, deep learning and for designing software applications using artificial intelligence; platform as a service (PAAS) providing online non-downloadable application programming interface (API) software for analyzing clinical data for scientific and medical research; providing online non-downloadable software widget for machine learning and for designing software applications using artificial intelligence; software as a service (SAAS) services featuring software for use in computer software development kits for use by developers to create computer software applications and interfaces in the fields of machine learning, cognitive computing, deep learning, artificial intelligence; customization of web software, namely, application programming interface design for others; providing online non-downloadable computer software for neuromorphic computing, namely software for replicating the processing of information in a manner which emulates biological human brain functions;
09 - Scientific and electric apparatus and instruments
Goods & Services
(1) Electronic data processing apparatus namely computers; computer chips; integrated circuit computer chip sets; microchips; neuromorphic computer chips; semiconductor processor chips; computer hardware to enable artificial intelligence applications; computer hardware to enable neuromorphic computation; neural network processors; neuromorphic data processors; integrated circuits; computers chips having a predefined architecture; computer software for neuromorphic computing, namely software based on the structures, processes and capacities of biological brains for creating artificial neural networks; downloadable computer software development kits for designing and developing software applications in the fields of machine learning, cognitive computing, deep learning, artificial intelligence; downloadable computer software application programs which implement software interfaces for designing and developing artificial intelligence software; downloadable computer software for the delivery of an artificial intelligence platform based on neuromorphic computation; downloadable software for use with artificial intelligence computer chips for designing and developing artificial intelligence computer systems; downloadable software for neuromorphic computing; downloadable software for building artificial intelligence platforms and artificial intelligence platforms based on neuromorphic computation; downloadable software developments kits for machine learning, cognitive computing, deep learning, artificial intelligence; downloadable application programming interface (API) software for analyzing clinical data for scientific and medical research; downloadable software in the nature of a software widget for machine learning and for designing software applications using artificial intelligence;
09 - Scientific and electric apparatus and instruments
42 - Scientific, technological and industrial services, research and design
Goods & Services
Electronic data processing apparatus; computer chips; computer chip sets; microchips; neuromorphic computer chips; semiconductor processor chips; computer hardware to enable artificial intelligence applications; computer hardware to enable neuromorphic computation; neural network processors being central processing units; neuromorphic data processors; integrated circuits; computers chips having a predefined architecture; downloadable computer software and computer hardware for information processing in which information is processed in a manner similar to the way the human brain processes information; downloadable computer software for designing and developing software applications; downloadable computer software application programs which implement software interfaces for designing and developing artificial intelligence software; electronic data processing apparatus for the delivery of an artificial intelligence platform based on neuromorphic computation; downloadable software for using artificial intelligence computer chips to design software applications; downloadable software for neuromorphic computing; downloadable software for building artificial intelligence platforms and artificial intelligence platforms based on neuromorphic computation; downloadable software for machine learning, cognitive computing, deep learning, and for designing software applications using artificial intelligence; downloadable application programming interface (API) software; downloadable software in the nature of a widget for machine learning and for designing software applications using artificial intelligence Providing online non-downloadable computer software for information processing in which information is processed in a manner similar to the way the human brain processes information
42 - Scientific, technological and industrial services, research and design
Goods & Services
Research, consulting and design services in the field of developing computer software, namely, artificial intelligence, neural networks; neuromorphic systems, neuromorphic computations and artificial neural networks related software; technical support services, namely, troubleshooting of computer software problems; computer programming services for others; non-downloadable software in the nature of a widget for machine learning and artificial intelligence; software as a service services featuring software for applications and interfaces for developers, namely, for the control and configuration of neuromorphic processor for Artificial Intelligence applications, and its associated user interface software; customization of web software, namely, application programming interface design for others
09 - Scientific and electric apparatus and instruments
Goods & Services
Electronic data processing apparatus; computer chips; computer chip sets; microchips; neuromorphic computer chips; semiconductor processor chips; computer hardware to enable artificial intelligence applications; computer hardware to enable neuromorphic computation; neural network processors being central processing units; neuromorphic data processors; integrated circuits; computers chips having a predefined architecture; downloadable computer software and computer hardware for information processing in which information is processed in a manner similar to the way the human brain processes information; downloadable computer software for designing and developing software applications; downloadable computer software application programs which implement software interfaces for designing and developing artificial intelligence software; electronic data processing apparatus for the delivery of an artificial intelligence platform based on neuromorphic computation; downloadable software for using artificial intelligence computer chips to design software applications; downloadable software for neuromorphic computing; downloadable software for building artificial intelligence platforms and artificial intelligence platforms based on neuromorphic computation; downloadable software for machine learning, cognitive computing, deep learning, and for designing software applications using artificial intelligence; downloadable application programming interface (API) software; downloadable software in the nature of a widget for machine learning and for designing software applications using artificial intelligence
42 - Scientific, technological and industrial services, research and design
Goods & Services
Research, consulting and design services concerning the development of computer software programs and architecture and computer hardware architecture; research, consulting and design services in the field of developing computer software for artificial intelligence, neural networks; computer network configuration services, namely, configuration of neuromorphic systems, neuromorphic computations and artificial neural networks; technical support services, namely, troubleshooting in the nature of diagnosing computer hardware and computer software problems; integration of computer hardware and software being computer services, namely, integration of computer software into computer hardware systems; computer software and hardware testing services; installation, updating and maintenance of computer software; computer programming services for others; providing online non-downloadable software for using artificial intelligence computer chips to design software applications; providing online non-downloadable software for neuromorphic computing; providing online non-downloadable software for building artificial intelligence platforms; providing online non-downloadable software for machine learning, cognitive computing, deep learning and for designing software applications using artificial intelligence; providing online non-downloadable application programming interface (API) software; providing online non-downloadable software in the nature of a widget for machine learning and for designing software applications using artificial intelligence; software as a service (SAAS) services featuring software for use in software development of applications and interfaces for developers; customization of web software, namely, application programming interface design for others; Providing online non-downloadable computer software for information processing in which information is processed in a manner similar to the way the human brain processes information
09 - Scientific and electric apparatus and instruments
Goods & Services
Electronic data processing apparatus; computer chips; computer chip sets; microchips; neuromorphic computer chips; semiconductor processor chips; computer hardware to enable artificial intelligence applications; computer hardware to enable neuromorphic computation; neural network processors being central processing units; neuromorphic data processors; integrated circuits; computers chips having a predefined architecture; downloadable computer software and computer hardware for information processing in which information is processed in a manner similar to the way the human brain processes information; downloadable computer software for designing and developing software applications; downloadable computer software application programs which implement software interfaces for designing and developing artificial intelligence software; electronic data processing apparatus for the delivery of an artificial intelligence platform based on neuromorphic computation; downloadable software for using artificial intelligence computer chips to design software applications; downloadable software for neuromorphic computing; downloadable software for building artificial intelligence platforms and artificial intelligence platforms based on neuromorphic computation; downloadable software for machine learning, cognitive computing, deep learning, and for designing software applications using artificial intelligence; downloadable application programming interface (API) software; downloadable software in the nature of a widget for machine learning and for designing software applications using artificial intelligence
42 - Scientific, technological and industrial services, research and design
Goods & Services
Application service provider featuring application programming interface (API) software for the control and configuration of a proprietary neuromorphic processor for Artificial Intelligence applications, and its associated user interface software
Embodiments of the present invention provides a system and method of learning and classifying features to identify objects in images using a temporally coded deep spiking neural network, a classifying method by using a reconfigurable spiking neural network device or software comprising configuration logic, a plurality of reconfigurable spiking neurons and a second plurality of synapses. The spiking neural network device or software further comprises a plurality of user-selectable convolution and pooling engines. Each fully connected and convolution engine is capable of learning features, thus producing a plurality of feature map layers corresponding to a plurality of regions respectively, each of the convolution engines being used for obtaining a response of a neuron in the corresponding region. The neurons are modeled as Integrate and Fire neurons with a non-linear time constant, forming individual integrating threshold units with a spike output, eliminating the need for multiplication and addition of floating-point numbers.
G11C 11/41 - Digital stores characterised by the use of particular electric or magnetic storage elementsStorage elements therefor using electric elements using semiconductor devices using transistors forming cells with positive feedback, i.e. cells not needing refreshing or charge regeneration, e.g. bistable multivibrator or Schmitt trigger
G11C 11/54 - Digital stores characterised by the use of particular electric or magnetic storage elementsStorage elements therefor using elements simulating biological cells, e.g. neuron
44.
EVENT-BASED CLASSIFICATION OF FEATURES IN A RECONFIGURABLE AND TEMPORALLY CODED CONVOLUTIONAL SPIKING NEURAL NETWORK
Embodiments of the present invention provides a system and method of learning and classifying features to identify objects in images using a temporally coded deep spiking neural network, a classifying method by using a reconfigurable spiking neural network device or software comprising configuration logic, a plurality of reconfigurable spiking neurons and a second plurality of synapses. The spiking neural network device or software further comprises a plurality of user-selectable convolution and pooling engines. Each fully connected and convolution engine is capable of learning features, thus producing a plurality of feature map layers corresponding to a plurality of regions respectively, each of the convolution engines being used for obtaining a response of a neuron in the corresponding region. The neurons are modeled as Integrate and Fire neurons with a non-linear time constant, forming individual integrating threshold units with a spike output, eliminating the need for multiplication and addition of floating-point numbers.
G06F 15/18 - in which a program is changed according to experience gained by the computer itself during a complete run; Learning machines (adaptive control systems G05B 13/00;artificial intelligence G06N)
G06G 7/00 - Devices in which the computing operation is performed by varying electric or magnetic quantities
45.
EVENT-BASED CLASSIFICATION OF FEATURES IN A RECONFIGURABLE AND TEMPORALLY CODED CONVOLUTIONAL SPIKING NEURAL NETWORK
Embodiments of the present invention provides a system and method of learning and classifying features to identify objects in images using a temporally coded deep spiking neural network, a classifying method by using a reconfigurable spiking neural network device or software comprising configuration logic, a plurality of reconfigurable spiking neurons and a second plurality of synapses. The spiking neural network device or software further comprises a plurality of user-selectable convolution and pooling engines. Each fully connected and convolution engine is capable of learning features, thus producing a plurality of feature map layers corresponding to a plurality of regions respectively, each of the convolution engines being used for obtaining a response of a neuron in the corresponding region. The neurons are modeled as Integrate and Fire neurons with a non-linear time constant, forming individual integrating threshold units with a spike output, eliminating the need for multiplication and addition of floating-point numbers.
Disclosed herein are system, method, and computer program product embodiments for an improved spiking neural network (SNN) configured to learn and perform unsupervised extraction of features from an input stream. An embodiment operates by receiving a set of spike bits corresponding to a set synapses associated with a spiking neuron circuit. The embodiment applies a first logical AND function to a first spike bit in the set of spike bits and a first synaptic weight of a first synapse in the set of synapses. The embodiment increments a membrane potential value associated with the spiking neuron circuit based on the applying. The embodiment determines that the membrane potential value associated with the spiking neuron circuit reached a learning threshold value. The embodiment then performs a Spike Time Dependent Plasticity (STDP) learning function based on the determination that the membrane potential value of the spiking neuron circuit reached the learning threshold value.
F, and a second output signal, different from the first one, for all other neurons. A digital electronic circuit and system configured for carrying out the above method.
Disclosed herein are system and method embodiments for establishing secure communication with a remote artificial intelligent device. An embodiment operates by capturing an auditory signal from an auditory source. The embodiment coverts the auditory signal into a plurality of pulses having a spatio-temporal distribution. The embodiment identifies an acoustic signature in the auditory signal based on the plurality of pulses using a spatio-temporal neural network. The embodiment modifies synaptic strengths in the spatio-temporal neural network in response to the identifying thereby causing the spatio-temporal neural network to learn to respond to the acoustic signature in the acoustic signal. The embodiment transmits the plurality of pulses to the remote artificial intelligent device over a communications channel thereby causing the remote artificial intelligent device to learn to respond to the acoustic signature, and thereby allowing secure communication to be established with the remote artificial intelligent device based on the auditory signature.
A method for creating a dynamic neural function library that relates to Artificial Intelligence systems and devices is provided. Within a dynamic neural network (artificial intelligent device), a plurality of control values are autonomously generated during a learning process and thus stored in synaptic registers of the artificial intelligent device that represent a training model of a task or a function learned by the artificial intelligent device. Control Values include, but are not limited to, values that indicate the neurotransmitter level that is present in the synapse, the neurotransmitter type, the connectome, the neuromodulator sensitivity, and other synaptic, dendric delay and axonal delay parameters. These values form collectively a training model. Training models are stored in the dynamic neural function library of the artificial intelligent device. The artificial intelligent device copies the function library to an electronic data processing device memory that is reusable to train another artificial intelligent device.
Embodiments of the present invention provide an artificial neural network system for improved machine learning, feature pattern extraction and output labeling. The system comprises a first spiking neural network and a second spiking neural network. The first spiking neural network is configured to spontaneously learn complex, temporally overlapping features arising in an input pattern stream. Competitive learning is implemented as Spike Timing Dependent Plasticity with lateral inhibition in the first spiking neural network. The second spiking neural network is connected with the first spiking neural network through dynamic synapses, and is trained to interpret and label the output data of the first spiking neural network. Additionally, the output of the second spiking neural network is transmitted to a computing device, such as a CPU for post processing.
09 - Scientific and electric apparatus and instruments
Goods & Services
Computer chips; Computer software and hardware for information processing in which information is processed in a manner similar to the way the human brain processes information, not for use for implantation into living creatures
52.
Intelligent autonomous feature extraction system using two hardware spiking neutral networks with spike timing dependent plasticity
Embodiments of the present invention provide an artificial neural network system for feature pattern extraction and output labeling. The system comprises a first spiking neural network and a second spiking neural network. The first spiking neural network is configured to autonomously learn complex, temporally overlapping features arising in an input pattern stream. Competitive learning is implemented as spike timing dependent plasticity with lateral inhibition in the first spiking neural network. The second spiking neural network is connected with the first spiking neural network through dynamic synapses, and is trained to interpret and label the output data of the first spiking neural network. Additionally, the labeled output of the second spiking neural network is transmitted to a computing device, such as a central processing unit for post processing.
The present invention provides a system and method for controlling a device by recognizing voice commands through a spiking neural network. The system comprises a spiking neural adaptive processor receiving an input stream that is being forwarded from a microphone, a decimation filter and then an artificial cochlea. The spiking neural adaptive processor further comprises a first spiking neural network and a second spiking neural network. The first spiking neural network checks for voice activities in output spikes received from artificial cochlea. If any voice activity is detected, it activates the second spiking neural network and passes the output spike of the artificial cochlea to the second spiking neural network that is further configured to recognize spike patterns indicative of specific voice commands. If the first spiking neural network does not detect any voice activity, it halts the second spiking neural network.
G10L 25/30 - Speech or voice analysis techniques not restricted to a single one of groups characterised by the analysis technique using neural networks
A configurable spiking neural network based accelerator system is provided. The accelerator system may be executed on an expansion card which may be a printed circuit board. The system includes one or more application specific integrated circuits comprising at least one spiking neural processing unit and a programmable logic device mounted on the printed circuit board. The spiking neural processing unit includes digital neuron circuits and digital, dynamic synaptic circuits. The programmable logic device is compatible with a local system bus. The spiking neural processing units contain digital circuits comprises a Spiking Neural Network that handles all of the neural processing. The Spiking Neural Network requires no software programming, but can be configured to perform a specific task via the Signal Coupling device and software executing on the host computer. Configuration parameters include the connections between synapses and neurons, neuron types, neurotransmitter types, and neuromodulation sensitivities of specific neurons.
09 - Scientific and electric apparatus and instruments
Goods & Services
Computer hardware and software for information processing in which information is processed in a manner similar to the way the human brain processes information, not for use for implantation into living creatures; computer chips not for use for implantation into living creatures
56.
Method and a system for creating dynamic neural function libraries
A method for creating a dynamic neural function library that relates to Artificial Intelligence systems and devices is provided. Within a dynamic neural network (artificial intelligent device), a plurality of control values are autonomously generated during a learning process and thus stored in synaptic registers of the artificial intelligent device that represent a training model of a task or a function learned by the artificial intelligent device. Control Values include, but are not limited to, values that indicate the neurotransmitter level that is present in the synapse, the neurotransmitter type, the connectome, the neuromodulator sensitivity, and other synaptic, dendric delay and axonal delay parameters. These values form collectively a training model. Training models are stored in the dynamic neural function library of the artificial intelligent device. The artificial intelligent device copies the function library to an electronic data processing device memory that is reusable to train another artificial intelligent device.
A hierarchical information processing system is disclosed having a plurality of artificial neurons, comprised of binary logic gates, and interconnected through a second plurality of dynamic artificial synapses, intended to simulate or extend the function of a biological nervous system. The system is capable of approximation, autonomous learning and strengthening of formerly learned input patterns. The system learns by simulated Synaptic Time Dependent Plasticity, commonly abbreviated to STDP. Each artificial neuron consisting of a soma circuit and a plurality of synapse circuits, whereby the soma membrane potential, the soma threshold value, the synapse strength and the Post Synaptic Potential at each synapse are expressed as values in binary registers, which are dynamically determined from certain aspects of input pulse timing, previous strength value and output pulse feedback.
