Systems and methods for multi-turn collaboration for machine-learned inference are provided. A method can include receiving, by a computing system comprising one or more computing devices, a first input. The method can include generating, by the computing system based on the first input, structured data indicative of one or more target output properties for a machine-learned inference operation. The method can include receiving, by the computing system, one or more second inputs indicative of one or more changes to the one or more target output properties. The method can include updating, by the computing system, the structured data indicative of the one or more target output properties based on the second input to generate updated structured data. The method can include generating, by the computing system using a machine-learned model and based at least in part on the updated structured data, an output.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting protein binders, e.g., for physical synthesis. In one aspect, a method comprises: determining, for each candidate protein binder in a set of candidate protein binders for a target molecule, one or more quality scores for the candidate protein binder; and selecting a proper subset of the set of candidate protein binders based at least in part on the quality scores.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for fine-tuning a target machine learning model to perform a target machine learning task. In one aspect, a method comprises: obtaining initial parameters for a target machine learning model; at each interpolation iteration of a sequence of interpolation iterations: training a plurality of auxiliary machine learning models to perform the target machine learning task using training data for the target machine learning task, interpolating the trained parameters for the plurality of auxiliary machine learning models for the interpolation iteration, and updating the current parameters for the target machine learning model using the interpolated parameters for the interpolation iteration; and, after the final interpolation iteration, determining a trained set of parameters for the target machine learning model based on the current parameters for the target machine learning model.
Systems and methods, implemented as computer programs on one or more computers for training a consistency model for use in generating a frame of data, such as a frame of image data, and methods of using a trained consistency model to generate a frame of data. A consistency model is used to generate a frame of data by predicting a succession of de-noised frames starting with an initial, noisy frame at an initial time and ending with a final frame, without noise, at a final time. The consistency model is trained to generate self-consistent predictions over a trajectory of predicted frames corresponding to these times. Implementations of the described techniques divide the trajectory into segments and only require the model to generate self-consistent predictions over each segment. This can facilitate the rapid generation of high quality frames of data.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for simulating industrial facilities for control. One of the methods includes. at each of a plurality of time steps during a task episode: receiving, from a computer simulator of an industrial facility, measurements representing a current state of the facility; generating, from the measurements, an observation; providing the observation as input to a control policy for controlling the facility; receiving, as output, an action for controlling one or more setpoints of the facility; generating, from the action, one or more control inputs for the one or more setpoints of the facility; and providing, as input to the simulator, (i) the control inputs and (ii) current values for one or more configuration parameters of the simulator to cause the simulator to generate, as output, new measurements representing a new state of the facility.
G05B 19/418 - Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a generative neural network. In particular, the generative neural network is trained on an objective function that includes multiple different objectives, with two or more of the objectives being reward objectives.
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
A method performed by one or more data processing apparatus for updating a representation of an environment comprising a plurality of point embeddings. Each point embedding is derived from features characterizing a corresponding spatial location in the environment. The method comprises: updating each of the point embeddings using a respective proper subset of the point embeddings, each subset being selected based on the spatial location of the point embedding; and updating the point embeddings by applying a linear self-attention mechanism over the point embeddings. Applying the linear self-attention mechanism over the point embeddings comprises: using the point embeddings to determine a query matrix, a key matrix and a value matrix; and updating the point embeddings using a matrix product of the query matrix, the key matrix, and the value matrix.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting labels for biological sequences. One of the methods includes, in response to receiving a request to identify labels associated with an input biological sequence: determining, for each of a plurality of candidate labels, a score characterizing a likelihood that the input biological sequence is associated with the candidate label. Each score is determined by identifying a plurality of positive biological sequences that are each associated with the candidate label; and processing a network input including the input biological sequence and the plurality of positive biological sequences using a neural network to generate the score characterizing the likelihood that the input biological sequence is associated with the candidate label. The method includes selecting one or more of the candidate labels as labels for the input biological sequence based on the scores.
Methods, systems, and apparatus for training a machine learning model through contrastive learning using a batch that includes a subset of training examples from a training dataset. In one aspect, a method includes obtaining a training dataset including multiple training examples and generating a batch comprising a subset of training examples. The method includes generating the batch by selecting the subset of training examples based on, for each training examples, a respective conditional score that measures a benefit to the training of the machine learning model of including the training example in the batch given that at least a subset of the training examples of the training dataset are also included in the batch. The method further includes training the machine learning model on a contrastive loss using the batch.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an output sequence that includes a respective token selected from a vocabulary of tokens at each of multiple output positions. In one aspect, one of the methods includes obtaining an initial output sequence, the initial output sequence comprising a mask token at each of at least a subset of the multiple output positions; repeatedly performing the following at each of multiple update iterations: obtaining an intermediate representation of the output sequence; generate a diffusion model output that comprises, for each of the multiple output positions, a respective score for each token in at least a subset of the vocabulary of tokens; determining, for each output position in the output sequence that is occupied by a mask token, a masked probability; selecting a subset of the multiple output positions; and generating an updated intermediate representation.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a student generator neural network to generate output data items using a teacher diffusion model based on Expectation-Maximization distillation. The generator neural network can be configured through training to generate any of a variety of output data items, e.g., image data items, audio data items, or video data items.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training neural network with explicit learning rate schedules. In one aspect, a method includes: obtaining a training dataset for training a neural network parametrized by a set of network parameters; and training the neural network on the training dataset over a number of training iterations, including, at each training iteration: obtaining current values of the network parameters; parametrizing the neural network with the current values of the network parameters; sampling, from the training dataset, a subset of training data; training the neural network on the subset of training data to generate updated values of the network parameters; determining whether a criterion is satisfied at the training iteration; and when the criterion is satisfied at the training iteration, normalizing the updated values of the network parameters.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating an audio signal. One of the methods includes receiving an input image; processing, using one or more generative neural networks, the input image to generate a music caption describing one or more audio features corresponding to the input image; and processing, using an audio generative neural network, the music caption to generate an audio signal described by the music caption.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing multi-modal inputs using denoising neural networks.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an audio signal. In one aspect, a method comprises obtaining a context input for generating the audio signal, wherein the context input comprises a plurality of inputs; processing each of the inputs using a corresponding encoder neural network to generate a respective representation of the input; processing the respective representations of the inputs using a shared encoder to generate an encoded representation; processing the encoded representation using a token decoder neural network to generate a sequence of output tokens representing the audio signal; and processing the sequence of output tokens representing the audio signal using an audio decoder neural network to generate the audio signal.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing images of a scene to generate a three-dimensional reconstruction of the scene. In one aspect, a method comprises: obtaining data characterizing a scene in an environment; determining a respective viewpoint for each of one or more target views of the scene; generating, using a multi-view generative model, a respective synthesized image for each of the one or more target views of the scene by processing (i) the data characterizing the scene and (ii) data characterizing the viewpoints for the one or more target views of the scene; and generating data characterizing a 3D representation of the scene based on the synthesized images for the one or more target views of the scene.
A method performed by one or more computers for training a machine learning model to determine a representation of a data item. The method comprises: obtaining training examples that each comprise (i) a training input comprising a set of data items and (ii) a training output identifying a target subset of the set of data items; processing the training examples to determine, for each training example, a corresponding target probability for the target subset given the set of data items of the training input. The machine learning model determines representations of the data items and processes the representations to determine a probability for the target subset. The machine learning model is trained by optimizing an objective function that compares the predicted probabilities with the corresponding target probabilities of the training examples.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing an input to generate an output for a machine learning task. One of the systems includes one or more computers and one or more storage devices storing instructions that, when executed by the one or more computers, cause the one or more computers to implement: a neural network. The neural network includes an expert retrieval layer. The expert retrieval layer includes (i) a plurality of expert neural networks that are each associated with a respective key and (ii) one or more query neural networks.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for processing an input sequence using a neural network that includes one or more mixture of depths attention layer blocks that can make dynamic token-level routing decisions across the depth of the network.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting operating states of power grids using graph neural networks.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling an agent interacting with an environment by selecting actions to be performed by the agent using an action selection neural network. In one aspect, a method comprises, at each of a plurality of action selection iterations: receiving data identifying a current observation and a current pre-committed sequence of actions; processing a network input comprising: (i) the current observation, and (ii) the current pre-committed sequence of actions, using the action selection neural network, to generate an action selection output; selecting a next sequence of actions based on the action selection output, wherein the next sequence of actions comprises a predefined number of actions that define a next pre-committed sequence of actions; and causing the agent to perform the next pre-committed sequence of actions after the agent has performed the current pre-committed sequence of actions.
Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for controlling an agent that is interacting in an environment by selecting actions to be performed by the agent and then causing the agent to perform the actions. That is, by receiving an observation image and obtaining an encoded representation of a natural language text sequence at a time step and, in response, selecting one or more actions to be performed by the agent, the described techniques can control an agent across many visually complex environments to perform arbitrary tasks that can be specified with natural language text instructions.
A method is proposed for training a media item encoder neural network. The media item encoder neural network is configured to receive a media item and to generate an output comprising feature data which is an encoding of the media item. The method comprises jointly training the media item encoder neural network and a decoder neural network. The decoder neural network is arranged to receive feature data output by the media item encoder neural network, and to generate text tokens based on the received feature data. The training is based on one or more training examples which each comprise a media item and a corresponding text token string. The corresponding text token strings of one or more of the training examples comprise first text tokens describing an object present in the corresponding media item, and second text tokens defining a position of the object in the media item.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing input sequences using a hybrid neural network implementing both attention and recurrence to perform one or more machine learning tasks. In one example, a method performed by one or more computers is described. The method includes: receiving an input sequence including a respective input token at each of a number of input positions; and processing the input sequence, using a neural network, to generate a network output. The neural network includes a number of layer blocks, including: (i) one or more attention layer blocks, and (ii) one or more recurrent layer blocks. Each attention layer block includes an attention layer configured to apply an attention mechanism. Each recurrent layer block includes a recurrent layer configured to apply a recurrent operation.
Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for optimizing a fitness of a molecule, where the fitness of the molecule is based on respective values for each of one or more target attributes of the molecule. That is, by using multiple optimization rounds, where each optimization round generates new candidate molecules using a diverse set of different molecule design techniques, the described techniques can optimize the fitness of the molecule to be significantly higher than would be the case using traditional approaches.
Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for predicting metric values of experiment outcomes. That is, by receiving and processing arbitrary settings data and metric data of an experiment and, in response, generating an output sequence of tokens from a vocabulary that represents a predicted value of the metric if the particular experiment is performed in accordance with the particular values for the settings for the particular experiment, the described techniques can leverage transfer learning across vastly different experiment classes and function as a universal predictor of metric values of experiment outcomes.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for calibrating an abstention policy to mitigate prediction errors by a neural network. In one aspect, a system comprises receiving an input prompt, processing the input prompt using a neural network to generate a plurality of candidate outputs for the input prompt, determining a similarity score that characterizes a similarity of each of the candidate outputs to each other candidate output, determining whether the similarity score satisfies an abstention threshold value, and in response to determining that the similarity score satisfies a criterion based on an abstention threshold value being satisfied, providing one or more of the candidate outputs as a generated response to the input prompt.
Systems, methods, and computer program code for training image generation neural network systems to generate good image representations using self-attention. Implementations of the systems predict image patch embeddings autoregressively and train on a denoising task, in particular using a diffusion model objective. Also image processing systems that use the generated image representations.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for simulating states of an environment over sequences of time steps. In one aspect, a method comprises, at each of a sequence of time steps: generating a graph representing an environment at the time step comprising a plurality of graph nodes and graph edges by, for each of one or more target objects in the environment for the time step: determining object-to-point distances between the target object and points associated with one or more neighboring objects based on a signed distance function for the target object; and creating one or more collision edges in the graph connecting graph nodes associated with the target object and the neighboring object based on the determined distances; and processing the graph using a graph neural network to generate an updated graph representing the environment at a next time step.
G06F 30/15 - Vehicle, aircraft or watercraft design
G06F 30/17 - Mechanical parametric or variational design
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating outputs using machine learning models. One of the methods includes receiving input data for a machine learning task; processing the input data to generate a respective output at each of one or more iterations, comprising, at each of the one or more iterations: processing an input for the iteration derived from the input data using a trained model that has been trained to perform one or more machine learning tasks; processing the input for the iteration using a task-specific model to generate a task-specific representation of the input for the machine learning task; for each adapting layer in a set of multiple adapting layers, processing an adapting layer input to generate a candidate output for the iteration; and generating the output for the iteration from the candidate outputs for the iteration generated by the adapting layers.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating controllable videos using generative neural networks.
A method of using a first and a second language model neural network to generate an output token sequence from an input token sequence is provided. At least the second network has been fine-tuned. The method comprises, for each position in the output token sequence: (i) generating, using the first network, a respective score for each token in the vocabulary based on the input token sequence and based on any previously selected tokens in the output token sequence, (ii) generating, using the second network, a respective score for each token in the vocabulary based on the input token sequence and based on any previously selected tokens in the output token sequence, (iii) combining, based on a realignment parameter, said scores, and (iv) selecting, for the respective position in the output sequence, a token based on the combined scores.
Methods, systems, and apparatus for generating a response to a query input. In one aspect, a method includes receiving a query input including a sequence of input tokens and processing the query input using a language model neural network to generate multiple candidate output sequences. Each candidate output sequence includes a sequence of output tokens from a vocabulary of output tokens. For each output token, the method further includes identifying, as response tokens, a subset of the output tokens in the candidate output sequence and determining, from scores assigned by the language model neural network while generating the response tokens, a confidence score for the candidate output sequence. The method further includes selecting one of the candidate output sequences based on the confidence scores for the response tokens and generating a response to the query input from the selected candidate output sequence.
A media element processing system, for media elements such as videos, comprises a memory which is augmented by a memory control unit in each of number of steps based on a corresponding current segment of the media element, by adding to it a memory element. The memory element is formed based on an embedding of the current segment of the media element, and comprises a smaller number of values than the embedding of the current segment. The system uses the memory to process current segments of the media element. The data stored in the memory may be informative about a large number of previous segments of the media element, while limiting the required size of the memory and the number of tunable parameters employed in the system.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network that has a plurality of neural network parameters. One of the methods includes, at each of a plurality of training steps: receiving one or more network inputs, each corresponding to a machine learning task to be performed; for each of the one or more network inputs: sampling from the neural network given the network input to generate a first network output and a second network output for the machine learning task; processing an annotating network input comprising the first network output and the second network output using an annotating neural network to generate an annotating network output; designating, based on at least the annotating network output, one of the first network output or the second network output as a preferred network output; and updating the neural network parameters to optimize an objective function.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating training an encoder neural network to generate discrete latent representations of data items by performing both a forward and a backward function during training.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes, for a weight tensor that includes weights of the neural network: performing, using a plurality of training examples, a training step to obtain respective gradients of a loss function with respect to the weights in the weight tensor; applying an optimizer to the respective gradients to generate respective gradient-based updates to the weights in the weight tensor; applying the respective gradient-based updates to the weights in the weight tensor to generate initial updated values of the weights in the weight tensor; scaling the initial updated values of the weights in the weight tensor to generate scaled updated values that have a predetermined target norm; and setting current values of the weights in the weight tensor for a next training step to be equal to the scaled updated values.
A method performed by one or more data processing apparatus. The method comprises receiving an image item; obtaining a mask for selecting portions of the image item; and generating, from the image item, one or more video item comprising a respective one or more sequences of image frames. Each image frame comprises a respective portion of the image item selected using the mask. For each image sequence, the mask is translated incrementally over the image item to select the respective portions of the image item for successive image frames in the sequence. The method further comprises performing a machine learning task by processing the one or more video items using a machine learning model.
Methods and systems for one or more computers, in which a method includes maintaining software tool use data that includes a software tool selection embedding and a respective software tool embedding for each software tool in a set of software tools. The method includes receiving a query input, generating a software tool selection input sequence, processing the software tool selection input sequence to generate a software tool selection output that identifies a particular software tool, and generating a software tool call input sequence that includes the respective software tool embedding for the particular software tool and an embedded characterization of the query input.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting weather using diffusion neural networks.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for predicting a 3D structure of a molecule complex In one aspect, there is provided a method comprising: obtaining a network input that characterizes a molecule complex; processing the network input characterizing the molecule complex using an embedding neural network to generate molecule embedding data; and generating, using a generative model and while the generative model is conditioned on the molecule embedding data, a predicted three-dimensional (3D) structure of the molecule complex that defines a respective predicted 3D spatial location of each atom in the molecule complex.
G16B 15/00 - ICT specially adapted for analysing two-dimensional or three-dimensional molecular structures, e.g. structural or functional relations or structure alignment
Implementations are provided for an intermediary machine learning model that enables conditioning between different pretrained machine learning models to perform non-native task(s). In various implementations, a first set of token(s) may be applied as inputs across initial layer(s) of a first pretrained machine learning model to generate a first set of raw activations. A second set of token(s) may be applied as inputs across initial layer(s) of a second pretrained machine learning model to generate a second set of raw activations. The raw activations may be processed using the intermediary machine learning model to generate first and second sets of steered activations. The first set of steered activations may be applied across subsequent layer(s) of the first pretrained machine learning model to generate first steered output(s). The second set of steered activations may be applied across subsequent layer(s) of the second pretrained machine learning model to generate second steered output(s).
Methods and systems for processing sequences using spectral state space models One of the methods includes, for successive time steps: processing an initial item embedding using an analysis network comprising processing layers arranged in a sequence, a first processing layer being configured to receive the initial item embedding, and to output a modified item embedding, and each other processing layer being configured to receive the item embedding output by the preceding layer and output a modified item embedding; wherein at least one of the processing layers is a spectral transform layer which, for each time step: generates a plurality of feature vectors by processing a sequence embedding using a plurality of spectral filters; multiplies the feature vectors by weight matrices, to form respective weighted feature vectors; and generates the modified item embedding for the time step including a term based on the weighted feature vectors.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing input sequences using a neural network that uses a partial position encoding scheme The neural network generally includes both global and local attention layers. In the partial position encoding scheme, while the local attention layers do use position encoding, (i) a subset of the global attention layers can apply an attention mechanism that does not use position encoding, or (ii) the subset of global attention layers can apply an attention mechanism that does not apply position encoding to one or more of the dimensions of the input to the attention mechanism.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating computer code using neural networks. One of the methods includes receiving description data describing a computer programming task; generating a plurality of candidate computer programs by sampling a plurality of output sequences from a set of one or more generative neural networks; clustering the plurality of candidate computer programs to generate a plurality of clusters; for each cluster in a set of one or more of the clusters: processing each of the respective plurality of candidate computer programs in the cluster using a correctness estimation neural network to generate a correctness score for the candidate computer program that estimates a likelihood that the candidate computer program accurately performs the computer programming task; and selecting a representative computer program for the cluster using the correctness scores for the respective plurality of candidate computer programs in the cluster; and selecting one or more of the representative computer programs for the clusters as synthesized computer programs for performing the computer programming task.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for partitioning the training of a neural network across multiple devices In particular, the training is partitioned using a schedule that includes multiple partitioning tactics.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a photomosaic of an input image or an input video using a text and image conditioned generative neural network. One of the methods includes receiving an input including a source image and, for each of a plurality of patches of the source image, one or more respective text descriptions; generating a photomosaic of the source image, where the photomosaic of the source image is an image that replaces each of the plurality of patches of the source image with a respective tile image that has one or more properties that are similar to one or more corresponding properties of the patch, and where the generating includes processing an image input includes the source image and the respective text descriptions for the plurality of patches using a text and image conditioned image generation neural network to generate the photomosaic.
Implementations are provided for leveraging video conference tools to streamline machine learning model training relating to robot (and non-robot) planning and/or control, and/or for subsequent robot management. In various implementations, video conference client(s) of a video conference session may render output that includes sensor feed(s) capturing an environment in which a robot operates. A robotic planner process may be communicatively coupled to the video conference session. A natural language (NL) request for the robot to perform a high-level task may be received. The robotic planner process may process the NL request using a first machine learning model to generate NL responses, each expressing a mid- level action to be performed by the robot to carry out a respective portion of the high-level task. In some implementations, the NL responses may be processed to generate robot control data that may be used to operate a robot.
A neural network system is trained to generate textual reports (that is, medical reports, such as radiology reports) from one or more medical images, by fine-tuning a pre-trained neural network system (a visual language model, "VLM") operative, upon receiving an input comprising at least one image and a textual input, to generate a value indicative of a predicted likelihood of one or more candidate text continuations of the textual input. The fine-tuning of the neural network system is performed to reduce the value of a cost function which includes a first prediction cost term based on a first training database including first training datasets of at least one medical image and an associated text report, the first training datasets corresponding to first individuals. The first prediction cost term further includes a cost value for each individual, inversely dependent on a likelihood value of the associated textual report, conditioned on the at least one medical image, and created by the neural network system.
G16H 10/60 - ICT specially adapted for the handling or processing of patient-related medical or healthcare data for patient-specific data, e.g. for electronic patient records
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating audio and, optionally, a corresponding image using generative neural networks. For example, a spectrogram of the audio can be generated using a hierarchy of diffusion neural networks.
G10H 1/00 - Details of electrophonic musical instruments
G10H 7/10 - Instruments in which the tones are synthesised from a data store, e.g. computer organs by calculating functions or polynomial approximations to evaluate amplitudes at successive sample points of a tone waveform using coefficients or parameters stored in a memory, e.g. Fourier coefficients
G10H 7/12 - Instruments in which the tones are synthesised from a data store, e.g. computer organs by calculating functions or polynomial approximations to evaluate amplitudes at successive sample points of a tone waveform by means of a recursive algorithm using one or more sets of parameters stored in a memory and the calculated amplitudes of one or more preceding sample points
Systems, methods, and program code for training an encoder neural network and de-noising decoder neural network for generating an output data item such as an image or audio Training source and target data items are obtained, representing views of an object or scene, and used to train the encoder neural network and the de-noising decoder neural network. The trained encoder neural network generates representations usable for many downstream tasks. The trained encoder neural network and de-noising decoder neural network can be used together to generate new views of objects or scenes, such as a new 3D view, given just one or a few source views.
Systems and methods for using a distributed computing system to train a large neural network to perform a machine learning task. A shared set of trainable parameters is maintained in a shared data store, and each of a geographically distributed set of workers updates their trainable parameters using a shard training dataset. There are two optimization processes: an outer optimization process, and an inner optimization loop that is executed by each worker independently and in parallel tens, hundreds, or thousands of times. The workers can have different computing capabilities and can be geographically distant from one another, and the communications bandwidth used by the system can be two or three orders of magnitude less than that of other systems.
A caption for a media data item, such as an image or video, is chosen from plurality of candidate captions. The choice is made using both a respective posterior probability of the media data item given the candidate caption, and a respective prior probability for the candidate caption.
Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for generating training data for training a vision language model. In particular, generating training data such that, once a vision language model has been trained on the training data, the vision language model ("vision language neural network") can accurately encode information about spatial properties of objects depicted in images that are provided as input to the vision language model. Because of how the described techniques generate training data, trained vision language models using the generated training data demonstrate significant improvements in performance on visual question and answering tasks compared to conventionally trained vision language models.
Systems and methods, implemented as computer programs on one or more computers in one or more locations, for generating a sequence of data elements using a neural network comprising a sequence of attention neural network layers. The sequence comprises a respective continuous valued data element at each position in a sequence of positions. Implementations of the described techniques remove the need for discrete tokens and fixed, finite vocabularies.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for processing a video that includes a plurality of video segments using neural networks to generate, for each video segment, an output that characterizes the video segment The neural networks include a video encoder neural network, a decoder neural network, and, optionally, in some implementations, a dimensionality reduction neural network and an autoregressive transformer neural network. Optionally, the neural networks have access to a retrieval dataset that stores a plurality of embeddings.
A machine learning model is trained using a subset of training examples from a store of training data. Rather than randomly selecting the subset, the training examples in the subset are selected based on a score obtained using an online model. The online model is also trained using the subset of training examples, before performing another selection. As such, each successive selection of a subset of the training data, which are then provided to the machine learning model for further training, contains training examples which are better suited for efficiently training the machine learning model.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a neural network. In one aspect, a method includes obtaining a temporal sequence of video frames and training the neural network on one or more superimposed initial video frame or one or more masked initial video frame that are generated based on video frames included in the temporal sequence. The temporal sequence includes one or more initial video frames at one or more initial time steps followed by one or more subsequent video frames at one or more subsequent time steps.
An image generation model generates a visual data item by auto-regressive process in which a set of initial data tokens is iteratively refined in multiple steps based on corresponding textual prompt items The visual data item is based on an output vector generated in one or more of the steps of the auto-regressive process. The textual prompt items are modified during the auto-regressive process by referencing additional ones of a set of concept definition datasets which define content to be included in the visual data item, so that the visual data item depicts content defined by the referenced concept definition datasets.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for encoding input data comprising input data values corresponding to respective input data grid points of an input data grid, such as image, video or audio data.
A computer-implemented method of training a neural network system comprising a visual encoder neural network and a text encoder neural network is provided The method comprises obtaining a plurality of training data items (each training data item comprising an image and associated text defining a sequence of text tokens) and at each of a plurality of training steps processing at least one of the training data items by: processing pixels of the image in the training data item using the visual encoder neural network to generate a set of patch embeddings for the image; processing the sequence of text tokens using the text encoder neural network to generate a sequence of token embeddings, processing the set of patch embeddings and the sequence of token embeddings to generate a set of language-aware patch embeddings (based on similarities between patch embeddings and token embeddings), and training at least the visual encoder neural network by backpropagating gradients of a contrastive objective function evaluated over the language-aware patch embeddings and the sequence of token embeddings.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a multimodal machine learning model to perform a machine learning task. The multimodal machine learning model is trained on noisy batches of training data from one or more noisy training datasets, and on task-specific batches of training data from one or more further, task-specific training datasets. The multimodal machine learning model is disproportionately trained on noisy batches of training data, for example by training the model using a proportion of noisy training batches in the training data that is greater than a proportion of a number of the noisy training datasets in a total number of training datasets.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for determining a size of a training data set for training a machine learning model In one aspect, the size is determined using a shrinking estimate that estimates how much training data is needed to train a smaller machine learning model to achieve the same performance as a larger machine learning model.
Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for determining a final computer program for performing a task by searching through a space of candidate computer programs That is, by starting with an initial computer program and using an evolutionary search procedure that uses a pre-trained language model to generate new candidate computer programs in conjunction with an evaluation function to verify the quality of the new candidate computer programs, the resulting final computer program can be determined in an automatic fashion and can perform the task (often using novel steps and processes) more effectively than the initial computer program for the task.
A method is proposed for generating a multi-modal language model (MMLM) neural network trained to perform a multi-modal task on an input data element comprising at least one media input (an image or sound signal) to generate a token output which is a text response to the input data element. The method employs a decoder network trained to use the token output to generate reconstructed media tokens. Repeated modifications are made to the MMLM to reduce a discrepancy between the reconstructed media tokens and media tokens generated from the media input(s) by a media encoder neural network.
A method is proposed for generating a visual language model (VLM) neural network trained to perform a multi-modal task on an input dataset comprising an input image to generate a token output which is a text response to the input dataset. The VLM is trained using a training database comprising tuples of sample input datasets and corresponding sample token outputs. The sample input dataset of some of the tuples comprises an image generated from a text description by a text-to-image model, and the corresponding sample token output comprises at least part of the text description.
Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for generating an imputation for a multi-agent interaction. Generating an imputation can include generating the imputation for the least core imputation problem using multiple levels of parallelism that solve a Lagrangian formulation of the least core imputation problem. That is, intra-hardware device parallelism, i.e., parallel processing hardware accelerators (e.g., multiple arithmetic logic units, multiple central processors, graphics processing units, tensor processing units, and other application-specific integrated circuits), and inter-hardware device parallelism, e.g., using more than one hardware device, can both be leveraged to achieve solutions to the least core imputation problem in times that are orders of magnitude faster than using conventional linear programing techniques.
G06F 18/2115 - Selection of the most significant subset of features by evaluating different subsets according to an optimisation criterion, e.g. class separability, forward selection or backward elimination
Systems, methods, and computer program code for controlling a robot that is interacting with an environment to perform a particular task The technique involves generating a 2D trajectory image representing a 2D trajectory sketch. The 2D trajectory sketch indicates a desired trajectory for a part of the robot, e.g. an end effector, when performing the task. A neural network system uses the 2D trajectory image as deliberately underspecified guidance for how to perform the task. Techniques for training the neural network system are also described.
G05B 19/42 - Recording and playback systems, i.e. in which the programme is recorded from a cycle of operations, e.g. the cycle of operations being manually controlled, after which this record is played back on the same machine
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for using a Transformer-based neural network to generate output sequences. To generate the output sequences, the Transformer-based neural network is configured to perform quantized inference.
G06F 18/2413 - Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on distances to training or reference patterns
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
A system that uses a graph neural network to determine a representation of a physical environment at a new time step The new time step can be before or after a current time step based on representations of the physical environment at the current time step and one or more other time steps, e.g. one or more time steps before and/or after the current time step. The representation of the physical environment at the new time step may, for example, be used to generate an image of the physical environment at the new time step. The system can be used for controlling a robot interacting with the physical environment. Some examples of the techniques are specifically adapted for implementation using hardware accelerator units.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a diffusion neural network using a differentiable reward function.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training an object detection model In particular, a system performs detection-oriented pre-training of the object detection model by pre-training at least a set of detection heads that output level-specific detection embeddings on image-text pairs.
G06V 10/25 - Determination of region of interest [ROI] or a volume of interest [VOI]
G06V 10/52 - Scale-space analysis, e.g. wavelet analysis
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
A computer-implemented method is provided for processing a training database for training a neural network to perform a computational task, the training database comprising training items, to obtain a weight value for each training item. The method comprises: for each of one or more attributes, determining a corresponding item attribute vector for each training item which is a vector indicative of a likelihood of the training item exhibiting the attribute; and for each training item determining a corresponding weight value by: defining a loss function of the weight values and the item attribute vectors; and updating the weight values to reduce the loss function. A corresponding computer system and computer program product are also provided.
G06F 18/214 - Generating training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/772 - Determining representative reference patterns, e.g. averaging or distorting patternsGenerating dictionaries
G06V 10/774 - Generating sets of training patternsBootstrap methods, e.g. bagging or boosting
G06V 10/80 - Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
G06V 20/40 - ScenesScene-specific elements in video content
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for determining a measure of bias for a trained neural network One of the methods includes obtaining a plurality of initial network inputs, wherein each of the initial network inputs has been classified as belonging to a respective ground truth class, and wherein each of the initial network inputs is associated with a corresponding feature value of a particular feature; processing each of the plurality of initial network inputs using a trained target neural network to generate a respective predicted network output for each initial network input; determining, for each class of the respective ground truth classes for the initial network inputs, a respective effect size; and determining a measure of bias of the trained target neural network with respect to the particular feature by aggregating the respective effect sizes over each of the respective ground truth classes.
A computer-implemented method of obtaining, for a multi-participant interaction is provided, in which each of a plurality of participants is able to perform one of a respective set of actions and each participant receives a reward defined by a respective reward function of the corresponding actions performed by the plurality of participants, corresponding action embeddings for one or more of the actions which one or more of the participants can perform.
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for calibrating correlated noise specific to a machine learning task In one aspect, there is provided a method for, at each of a plurality of training iterations, receiving a set of one or more inputs and generating a respective output for each input, determining a gradient with respect to the network parameters of an objective function for the machine learning task, calibrating a noise correlation matrix specific to the machine learning task and an index of the training iteration by generating a correlation weight matrix parameterized as a function of a tuneable noise correlation parameter and the index of the training iteration, generating a correlated-noise gradient using the calibrated noise correlation matrix, and using the correlated-noise gradient to update the values of the plurality of network parameters.
Systems, methods, and computer program code for generating a task-prompt for inclusion in a model input for controlling a model to perform a task. An evolutionary process is used to evolve prompts that increasingly improve the extraction of knowledge from a machine learned model. Some machine learned model, such as Large Language Models, can consume significant computing resources, and implementations of the described techniques are configured to use parallel processing in a way that facilitates makes efficient use of these resources.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for training a high-level controller neural network for controlling an agent In particular, the high-level controller neural network generates natural language commands that can be provided as input to a low-level controller neural network, which generates control outputs that can be used to control the agent.
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
G06N 3/0442 - Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for receiving a data item of a first modality that is not text and generating a compressed data item Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for receiving a compressed data item and generating a lossless reconstruction of the data item of a first modality that is not text. Compressing data items and decompressing compressed data items both include the use of language model neural networks to uncover the complex structure within data items. For compressing data items, the use of the language model neural network allows compression systems to achieve better compression rates than traditional methods across a range of data modalities that are not text.
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling a robot using language model programs. A language model program is a computer program generated from an output of a code generation neural network, e.g., one that has been trained on a language modeling objective on computer code data.
Systems and methods for controlling agents using tracked points in images For example, controlling a mechanical agent that is interacting in a real-world environment by selecting action to be performed by the agent to perform instances of a task using images captured while the agent performs the instance of the task.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a data item using a diffusion neural network or other generative neural network.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a data item using a diffusion neural network or other generative neural network.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a data item using a diffusion neural network or other generative neural network.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating a data item using a diffusion neural network or other generative neural network.
Systems and methods for sub-additive action planning using multiple action selection policies. For example, sub-additive action planning can be performed using statistics of different tree searches that are guided by different action selection policies. As another example, multiple different action selection policies can be learned using intrinsic rewards that encourage diversity.
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a generative neural network. One of the methods includes training a generative neural network by performing a sequence of a plurality training stages each generating an expanded training data set. The method also involves performing a sequence of improve steps, each comprising training the generative neural network on the training examples in a corresponding subset of the expanded training data set.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for conformal prediction using ambiguous calibration examples. In particular, how to perform conformal prediction using calibration examples that include plausibility distributions is described.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06N 3/042 - Knowledge-based neural networksLogical representations of neural networks
Methods and systems for controlling agents, e.g., robots, using tokenized goal images. One of the methods includes receiving a goal image; tokenizing the goal image to generate a plurality of visual tokens; at each of a plurality of time steps: obtaining one or more observation images characterizing a state of the environment at the time step; tokenizing each of the one or more observation images; generating a sequence of input tokens that comprises the plurality of visual tokens that represent the goal image and the plurality of visual tokens that represent the one or more observation images; processing the sequence of input tokens to generate an output sequence of output tokens from the discrete vocabulary of tokens that represents an action to be performed by the agent in response to the observation images; and causing the agent to perform the selected action.
Systems and methods for designing a logic circuit For example, the logic circuit can be designed by training a circuit neural network that represents the circuit.
G06F 30/27 - Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for designing proteins. In one aspect, a method comprises: generating noisy molecular structure data sampled from a noise distribution that defines, for each position in an amino acid sequence of the protein, a corresponding initial spatial position for each atom in a predefined set of possible atoms; and processing the noisy molecular structure data using a diffusion model that comprises a denoising neural network to generate denoised molecular structure data that defines a denoised version of the noisy molecular structure data.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for obtaining one or more final policies for controlling an agent in an environment. In one aspect, one of the methods include: obtaining a candidate policy set that includes a plurality of candidate policies for controlling an agent in an environment; obtaining an offline dataset that stores a plurality of history trajectories, wherein each history trajectory comprises a plurality of history observations that each characterize a respective history state of the environment; and generating a behavioral representation for each candidate policy.
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Computer-implemented methods, systems, and software for image processing. A particular image processing task to be performed is defined by a set of task examples that demonstrate the task. A memory stores keys and values based on the task examples, and a task image on which the particular image processing task is to be performed is processed using an image encoder to obtain a task image feature vector for each of a plurality of spatial locations in the task image. The task image feature vectors for the spatial locations are used to obtain query vectors that are applied to the memory using a query-key-value attention mechanism, to obtain predicted local label values that, in turn, provide a result for the image processing task.
G06V 10/764 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
G06V 10/82 - Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Systems and methods, implemented as computer programs on one or more computers in one or more locations, for learning to control an agent to perform a task. The method involves training a policy neural network on demonstration actions that perform the task to obtain an initial, cloned action selection policy, determining a shaped reward using the cloned policy, then using the shaped reward to fine tune the policy neural network. The system can transition smoothly between learning to copy actions of a task demonstrated by an agent such as a human expert, and refining the learned actions. The system can also learn to recover gracefully when outside a distribution of actions of the demonstrating agent.
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for controlling agents using sequence-processing neural networks. In particular, the sequence-processing neural network is used as a dynamics model of the environment in order to perform planning when selecting actions to be performed by an agent.
G06N 3/006 - Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for verifying the provenance of a digital object generated by a neural network, such as an image or audio object. Also methods, systems, and apparatus, including computer programs, for training a watermarking neural network and a watermark decoding neural network. The described techniques make efficient use of computing resources and are robust to attack.
G06F 16/907 - Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
G06F 21/16 - Program or content traceability, e.g. by watermarking
G06N 3/084 - Backpropagation, e.g. using gradient descent
G10L 19/018 - Audio watermarking, i.e. embedding inaudible data in the audio 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
97.
MULTI-STAGE WATERMARKING OF A DIGITAL OBJECT GENERATED BY A MACHINE LEARNING MODEL
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for watermarking a digital object generated by a machine learning model. The digital object is defined by a sequence of tokens. The watermarking involves modifying a probability distribution of the tokens by applying a succession of watermarking stages.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for applying classifiers to messages between a user and a machine learning model.
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for optimizing a memory allocation of a target program using a state representation neural network.
patents
