Abstract

Systems and methods for a sensor hub system that accurately and efficiently performs sensory analysis across a broad range of users and sensors and is capable of recognizing a broad set of sensor-based events of interest using flexible and modifiable neural networks are disclosed. The disclosed solution consumes orders of magnitude less power than typical application processors. In one embodiment, a scalable sensor hub system for detecting sensory events of interest comprises a neural network and one or more sensors. The neural network comprises one or more dedicated low-power processors and memory storing one or more neural network programs for execution by the one or more processors. The output of the one or more sensors is converted into a spike signal, and the neural network takes the spike signal as input and determines whether a sensory event of interest has occurred.

IPC Classes  ?

• B25J 9/00 - Programme-controlled manipulators
• G06E 1/00 - Devices for processing exclusively digital data
• G06E 3/00 - Devices not provided for in group , e.g. for processing analogue or hybrid data
• 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
• G06G 3/02 - Devices in which the computing operation is performed mechanically for performing additions or subtractions, e.g. differential gearing
• G06G 3/04 - Devices in which the computing operation is performed mechanically for performing multiplications or divisions, e.g. variable-ratio gearing

Abstract

Systems and methods achieving scalable and efficient connectivity in neural algorithms by re-calculating network connectivity in an event-driven way are disclosed. The disclosed solution eliminates the storing of a massive amount of data relating to connectivity used in traditional methods. In one embodiment, a deterministic LFSR is used to quickly, efficiently, and cheaply re-calculate these connections on the fly. An alternative embodiment caches some or all of the LFSR seed values in memory to avoid sequencing the LFSR through all states needed to compute targets for a particular active neuron. Additionally, connections may be calculated in a way that generates neural networks with connections that are uniformly or normally (Gaussian) distributed.

IPC Classes  ?

• G06N 3/04 - Architecture, e.g. interconnection topology
• G06N 3/08 - Learning methods

Abstract

Systems and methods achieving scalable and efficient connectivity in neural algorithms by re-calculating network connectivity in an event-driven way are disclosed. The disclosed solution eliminates the storing of a massive amount of data relating to connectivity used in traditional methods. In one embodiment, a deterministic LFSR is used to quickly, efficiently, and cheaply re-calculate these connections on the fly. An alternative embodiment caches some or all of the LFSR seed values in memory to avoid sequencing the LFSR through all states needed to compute targets for a particular active neuron. Additionally, connections may be calculated in a way that generates neural networks with connections that are uniformly or normally (Gaussian) distributed.

IPC Classes  ?

• G06N 3/02 - Neural networks

Abstract

A learn-by-example (LBE) system comprises, among other things, a first component which provides examples of data of interest (Supply Component/Example Data Component); a second component capable of selecting and configuring a classification algorithm to classify the collected data (Configuration Component), and a third component capable of using the configured classification algorithm to classify new data from the sensors (Recognition Component). Together, these components detect sensory events of interest utilizing an LBE methodology, thereby enabling continuous sensory processing without the need for specialized sensor processing expertise and specialized domain-specific algorithm development.

IPC Classes  ?

• G06E 1/00 - Devices for processing exclusively digital data