Google Inc.

Openai Opco, LLC

Deepmind Technologies Limited

Ilya Sutskever

Quoc V Le

Geoffrey Everest Hinton

Alexander Krizhevsky

Jeffrey Adgate Dean

Oriol Vinyals

Gregory Sean Corrado

Navdeep Jaitly

Wojciech Zaremba

Samuel Bengio

Nitish Srivastava

Chung-Cheng Chiu

Tomas Mikolov

Mark Chen

Tao Xu

Minh-Thang Luong

Henrique Ponde De Oliveira Pinto

Jaroslaw Tworek

Hee Woo Jun

Christine McLeavey-Payne

Greg Brockman

Jong Wook Kim

Alec Radford

Yuping Luo

David Silver

Sergey Levine

Lukasz Mieczyslaw Kaiser

Timothy Paul Lillicrap

Alexander Benjamin Graves

Gregory Duncan Wayne

Ivo Danihelka

Karol Piotr Kurach

Shixiang Gu

Laurent Sifre

Thore Kurt Hartwig Graepel

Arthur Clement Guez

Arvind Neelakantan

Christopher Maddison

Shih-Chieh Huang

Nitish Srivastva

Sergey Vladimir Levine

Marcin Andrychowicz

V Le Quoc

Disclosed herein are methods, systems, and computer-readable media for generating an output transcript from an input audio segment using a multi-task transformer model. In some embodiments, the transformer model can be trained to transcribe or translate audio data in multiple languages using labeled audio data. The labeled audio data can include first audio segments associated with first same-language transcripts of the first audio segments and second audio segments associated with second different-language transcripts of the second audio segments. In some embodiments, a vocabulary of the model can include special purpose and time stamp tokens. The special purpose tokens can specify tasks for the model to perform.

Multi-task automatic speech recognition system

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting likelihoods of conditions being satisfied using recurrent neural networks. One of the systems is configured to process a temporal sequence comprising a respective input at each of a plurality of time steps and comprises: one or more recurrent neural network layers; one or more logistic regression nodes, wherein each of the logistic regression nodes corresponds to a respective condition from a predetermined set of conditions, and wherein each of the logistic regression nodes is configured to, for each of the plurality of time steps: receive the network internal state for the time step; and process the network internal state for the time step in accordance with current values of a set of parameters of the logistic regression node to generate a future condition score for the corresponding condition for the time step.

Predicting likelihoods of conditions being satisfied using neural networks

Disclosed herein are methods, systems, and computer-readable media for generating computer code based on natural language input. In an embodiment, a method may comprise one or more of: receiving a docstring representing natural language text specifying a digital programming result; generating, using a trained machine learning model, and based on the docstring, a computer code sample configured to produce respective candidate results; causing the computer code sample to be executed; identifying, based on the executing, a computer code sample configured to produce a particular candidate result associated with the digital programming result; performing at least one of outputting, via a user interface, the identified computer code sample, compiling the identified computer code sample, transmitting the identified computer code sample to a recipient device, storing the identified computer code sample, and/or re-executing the identified computer code sample.

Systems and methods for generating code using language models trained on computer code

Disclosed herein are methods, systems, and computer-readable media for generating natural language based on computer code input. In an embodiment, a method may comprise one or more of: accessing a docstring generation model configured to generate docstrings from computer code; receiving one or more computer code samples; generating, using the docstring generation model and based on the received one or more computer code samples, one or more candidate docstrings representing natural language text, each of the one or more candidate docstrings being associated with at least a portion of the one or more computer code samples; identifying at least one of the one or more candidate docstrings that provides an intent of the at least a portion of the one or more computer code samples; and/or outputting, via a user interface, the at least one identified docstring with the at least a portion of the one or more computer code samples.

Systems and methods for generating natural language using language models trained on computer code

A parallel convolutional neural network is provided. The CNN is implemented by a plurality of convolutional neural networks each on a respective processing node. Each CNN has a plurality of layers. A subset of the layers are interconnected between processing nodes such that activations are fed forward across nodes. The remaining subset is not so interconnected.

System and method for parallelizing convolutional neural networks

A system for training a neural network. A switch is linked to feature detectors in at least some of the layers of the neural network. For each training case, the switch randomly selectively disables each of the feature detectors in accordance with a preconfigured probability. The weights from each training case are then normalized for applying the neural network to test data.

System and method for addressing overfitting in a neural network

Predicting likelihoods of conditions being satisfied using recurrent neural networks

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for computing Q values for actions to be performed by an agent interacting with an environment from a continuous action space of actions. In one aspect, a system includes a value subnetwork configured to receive an observation characterizing a current state of the environment and process the observation to generate a value estimate; a policy subnetwork configured to receive the observation and process the observation to generate an ideal point in the continuous action space; and a subsystem configured to receive a particular point in the continuous action space representing a particular action; generate an advantage estimate for the particular action; and generate a Q value for the particular action that is an estimate of an expected return resulting from the agent performing the particular action when the environment is in the current state.

Reinforcement learning using advantage estimates

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating representations of input sequences. One of the methods includes obtaining an input sequence, the input sequence comprising a plurality of inputs arranged according to an input order; processing the input sequence using a first long short term memory (LSTM) neural network to convert the input sequence into an alternative representation for the input sequence; and processing the alternative representation for the input sequence using a second LSTM neural network to generate a target sequence for the input sequence, the target sequence comprising a plurality of outputs arranged according to an output order.

Generating representations of input sequences using neural networks

A system can be configured to perform tasks such as converting recorded speech to a sequence of phonemes that represent the speech, converting an input sequence of graphemes into a target sequence of phonemes, translating an input sequence of words in one language into a corresponding sequence of words in another language, or predicting a target sequence of words that follow an input sequence of words in a language (e.g., a language model). In a speech recognizer, the RNN system may be used to convert speech to a target sequence of phonemes in real-time so that a transcription of the speech can be generated and presented to a user, even before the user has completed uttering the entire speech input.

Generating target sequences from input sequences using partial conditioning

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for augmenting neural networks with an external memory using reinforcement learning. One of the methods includes providing an output derived from the system output portion of the neural network output as a system output in the sequence of system outputs; selecting a memory access process from a predetermined set of memory access processes for accessing the external memory from the reinforcement learning portion of the neural network output; writing and reading data from locations in the external memory in accordance with the selected memory access process using the differentiable portion of the neural network output; and combining the data read from the external memory with a next system input in the sequence of system inputs to generate a next neural network input in the sequence of neural network inputs.

Augmenting neural networks with external memory using reinforcement learning

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for implementing a convolutional gated recurrent neural network (CGRN). In one of the systems, the CGRN is configured to maintain a state that is a tensor having dimensions x by y by m, wherein x, y, and m are each greater than one, and for each of a plurality of time steps, update a currently maintained state by processing the currently maintained state through a plurality of convolutional gates.

Convolutional gated recurrent neural networks

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing operations using data from a data source. In one aspect, a method includes a neural network system including a controller neural network configured to: receive a controller input for a time step and process the controller input and a representation of a system input to generate: an operation score distribution that assigns a respective operation score to an operation and a data score distribution that assigns a respective data score in the data source. The neural network system can also include an operation subsystem configured to: perform operations to generate operation outputs, wherein at least one of the operations is performed on data in the data source, and combine the operation outputs in accordance with the operation score distribution and the data score distribution to generate a time step output for the time step.

Neural network programmer

Growing community of inventors

San Francisco, CA, United States of America

Ilya Sutskever