Patents by Inventor Aidan Nicholas Gomez
Aidan Nicholas Gomez has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240144006Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: ApplicationFiled: January 8, 2024Publication date: May 2, 2024Inventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Patent number: 11893483Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: GrantFiled: August 7, 2020Date of Patent: February 6, 2024Assignee: Google LLCInventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Patent number: 11803711Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.Type: GrantFiled: November 20, 2020Date of Patent: October 31, 2023Assignee: Google LLCInventors: Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Francois Chollet
-
Patent number: 11494561Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for training a machine learning model to perform multiple machine learning tasks from multiple machine learning domains. One system includes a machine learning model that includes multiple input modality neural networks corresponding to respective different modalities and being configured to map received data inputs of the corresponding modality to mapped data inputs from a unified representation space; an encoder neural network configured to process mapped data inputs from the unified representation space to generate respective encoder data outputs; a decoder neural network configured to process encoder data outputs to generate respective decoder data outputs from the unified representation space; and multiple output modality neural networks corresponding to respective different modalities and being configured to map decoder data outputs to data outputs of the corresponding modality.Type: GrantFiled: August 4, 2020Date of Patent: November 8, 2022Assignee: Google LLCInventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Ashish Teku Vaswani
-
Publication number: 20220051099Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: ApplicationFiled: September 3, 2021Publication date: February 17, 2022Inventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Patent number: 11113602Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: GrantFiled: July 17, 2020Date of Patent: September 7, 2021Assignee: Google LLCInventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Patent number: 10956819Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: GrantFiled: August 7, 2020Date of Patent: March 23, 2021Assignee: Google LLCInventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Publication number: 20210073481Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.Type: ApplicationFiled: November 20, 2020Publication date: March 11, 2021Inventors: Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Francois Chollet
-
Publication number: 20210019624Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: ApplicationFiled: August 7, 2020Publication date: January 21, 2021Inventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Publication number: 20210019623Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: ApplicationFiled: August 7, 2020Publication date: January 21, 2021Inventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Patent number: 10853590Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.Type: GrantFiled: November 19, 2019Date of Patent: December 1, 2020Assignee: Google LLCInventors: Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Francois Chollet
-
Publication number: 20200372358Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: ApplicationFiled: August 7, 2020Publication date: November 26, 2020Inventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Publication number: 20200372357Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: ApplicationFiled: July 17, 2020Publication date: November 26, 2020Inventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Publication number: 20200364405Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for training a machine learning model to perform multiple machine learning tasks from multiple machine learning domains. One system includes a machine learning model that includes multiple input modality neural networks corresponding to respective different modalities and being configured to map received data inputs of the corresponding modality to mapped data inputs from a unified representation space; an encoder neural network configured to process mapped data inputs from the unified representation space to generate respective encoder data outputs; a decoder neural network configured to process encoder data outputs to generate respective decoder data outputs from the unified representation space; and multiple output modality neural networks corresponding to respective different modalities and being configured to map decoder data outputs to data outputs of the corresponding modality.Type: ApplicationFiled: August 4, 2020Publication date: November 19, 2020Inventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Ashish Teku Vaswani
-
Patent number: 10789427Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for training a machine learning model to perform multiple machine learning tasks from multiple machine learning domains. One system includes a machine learning model that includes multiple input modality neural networks corresponding to respective different modalities and being configured to map received data inputs of the corresponding modality to mapped data inputs from a unified representation space; an encoder neural network configured to process mapped data inputs from the unified representation space to generate respective encoder data outputs; a decoder neural network configured to process encoder data outputs to generate respective decoder data outputs from the unified representation space; and multiple output modality neural networks corresponding to respective different modalities and being configured to map decoder data outputs to data outputs of the corresponding modality.Type: GrantFiled: November 19, 2019Date of Patent: September 29, 2020Assignee: Google LLCInventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Ashish Teku Vaswani
-
Patent number: 10719764Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: GrantFiled: September 3, 2019Date of Patent: July 21, 2020Assignee: Google LLCInventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Publication number: 20200089755Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for training a machine learning model to perform multiple machine learning tasks from multiple machine learning domains. One system includes a machine learning model that includes multiple input modality neural networks corresponding to respective different modalities and being configured to map received data inputs of the corresponding modality to mapped data inputs from a unified representation space; an encoder neural network configured to process mapped data inputs from the unified representation space to generate respective encoder data outputs; a decoder neural network configured to process encoder data outputs to generate respective decoder data outputs from the unified representation space; and multiple output modality neural networks corresponding to respective different modalities and being configured to map decoder data outputs to data outputs of the corresponding modality.Type: ApplicationFiled: November 19, 2019Publication date: March 19, 2020Inventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Ashish Teku Vaswani
-
Publication number: 20200089772Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media for performing machine translation tasks. One method includes receiving an input text segment in an input language; processing the input text segment using an encoder neural network to generate an encoder neural network output, the encoder neural network comprising multiple depth wise separable convolutional neural network layers; processing the encoder neural network output using an autoregressive decoder neural network to generate a decoder neural network output; and processing the decoder neural network output to generate a predicted output text segment in a target natural language.Type: ApplicationFiled: November 19, 2019Publication date: March 19, 2020Inventors: Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Francois Chollet
-
Publication number: 20190392319Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: ApplicationFiled: September 3, 2019Publication date: December 26, 2019Inventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani
-
Patent number: 10452978Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. In one aspect, one of the systems includes an encoder neural network configured to receive the input sequence and generate encoded representations of the network inputs, the encoder neural network comprising a sequence of one or more encoder subnetworks, each encoder subnetwork configured to receive a respective encoder subnetwork input for each of the input positions and to generate a respective subnetwork output for each of the input positions, and each encoder subnetwork comprising: an encoder self-attention sub-layer that is configured to receive the subnetwork input for each of the input positions and, for each particular input position in the input order: apply an attention mechanism over the encoder subnetwork inputs using one or more queries derived from the encoder subnetwork input at the particular input position.Type: GrantFiled: June 28, 2018Date of Patent: October 22, 2019Assignee: Google LLCInventors: Noam M. Shazeer, Aidan Nicholas Gomez, Lukasz Mieczyslaw Kaiser, Jakob D. Uszkoreit, Llion Owen Jones, Niki J. Parmar, Illia Polosukhin, Ashish Teku Vaswani