公开(公告)号：US10521701B2

公开(公告)日：2019-12-31

申请号：US16417190

申请日：2019-05-20

Applicant: Google LLC

Inventor： Noam M. Shazeer ,  Jakob D. Uszkoreit ,  Mitchell Thomas Stern

IPC: G06F15/18 ,  G06K9/62 ,  G06N20/00 ,  G06N7/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing parallel generation of output from an autoregressive sequence to sequence model. In one aspect, a blockwise parallel decoding method takes advantage of the fact that some architectures can score sequences in sublinear time. By generating predictions for multiple time steps at once then backing off to a longest prefix validated by the scoring model, the methods can substantially improve the speed of greedy decoding without compromising performance.

公开(公告)号：US10055461B1

公开(公告)日：2018-08-21

申请号：US14815736

申请日：2015-07-31

Applicant: Google LLC

Inventor： Jeremy Bem ,  Georges R. Harik ,  Joshua L. Levenberg ,  Noam M. Shazeer ,  Simon Tong

IPC: G06F17/30 ,  G06N99/00 ,  G06N7/00

CPC classification number: G06F16/24575 ,  G06F16/24578 ,  G06F16/3346 ,  G06F16/355 ,  G06F16/951 ,  G06F16/9535 ,  G06N7/005 ,  G06N20/00 ,  Y10S707/99933 ,  Y10S707/99935 ,  Y10S707/99943

Abstract: A system ranks documents based, at least in part, on a ranking model. The ranking model may be generated to predict the likelihood that a document will be selected. The system may receive a search query and identify documents relating to the search query. The system may then rank the documents based, at least in part, on the ranking model and form search results for the search query from the ranked documents.

公开(公告)号：US12299572B2

公开(公告)日：2025-05-13

申请号：US18403939

申请日：2024-01-04

Applicant: Google LLC

Inventor： Noam M. Shazeer ,  Lukasz Mieczyslaw Kaiser ,  Etienne Pot ,  Mohammad Saleh ,  Ben David Goodrich ,  Peter J. Liu ,  Ryan Sepassi

IPC: G06N3/08 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output sequence from an input sequence. One of the methods includes, at each of a plurality of generation time steps: generating a combined sequence for the generation time step that includes the input sequence followed by the output tokens that have already been generated as of the generation time step; processing the combined sequence using a self-attention decoder neural network to generate a time step output that defines a score distribution over a set of possible output tokens; and selecting, using the time step output, an output token from the set of possible output tokens as the next output token in the output sequence.

公开(公告)号：US12217173B2

公开(公告)日：2025-02-04

申请号：US17467096

申请日：2021-09-03

Applicant: Google LLC

Inventor： Noam M. Shazeer ,  Aidan Nicholas Gomez ,  Lukasz Mieczyslaw Kaiser ,  Jakob D. Uszkoreit ,  Llion Owen Jones ,  Niki J. Parmar ,  Illia Polosukhin ,  Ashish Teku Vaswani

IPC: G06N20/00 ,  G06N3/04 ,  G06N3/045 ,  G06N3/08

Abstract: 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.

公开(公告)号：US20250021799A1

公开(公告)日：2025-01-16

申请号：US18776868

申请日：2024-07-18

Applicant: Google LLC

Inventor： Noam M. Shazeer ,  Azalia Mirhoseini ,  Krzysztof Stanislaw Maziarz

IPC: G06N3/045 ,  G06N3/08

Abstract: A system includes a neural network that includes a Mixture of Experts (MoE) subnetwork between a first neural network layer and a second neural network layer. The MoE subnetwork includes multiple expert neural networks. Each expert neural network is configured to process a first layer output generated by the first neural network layer to generate a respective expert output. The MoE subnetwork further includes a gating subsystem that selects, based on the first layer output, one or more of the expert neural networks and determine a respective weight for each selected expert neural network, provides the first layer output as input to each of the selected expert neural networks, combines the expert outputs generated by the selected expert neural networks in accordance with the weights for the selected expert neural networks to generate an MoE output, and provides the MoE output as input to the second neural network layer.

公开(公告)号：US20240403639A1

公开(公告)日：2024-12-05

申请号：US18797915

申请日：2024-08-08

Applicant: Google LLC

Inventor： Daniel De Freitas Adiwardana ,  Noam M. Shazeer

IPC: G06N3/08 ,  G06F18/2113 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for evaluating candidate output sequences using language model neural networks. In particular, an auto-regressive language model neural network is used to generate a candidate output sequence. The same auto-regressive language model neural network is used to evaluate the candidate output sequence to determine rating scores for each of one or more criteria. The rating score(s) are then used to determine whether to provide the candidate output sequence.

公开(公告)号：US12142034B2

公开(公告)日：2024-11-12

申请号：US18388178

申请日：2023-11-08

Applicant: Google LLC

Inventor： Noam M. Shazeer ,  Lukasz Mieczyslaw Kaiser ,  Jakob D. Uszkoreit ,  Niki J. Parmar ,  Ashish Teku Vaswani

IPC: G06V10/82 ,  G06F18/21 ,  G06F18/213 ,  G06F18/28 ,  G06N3/04 ,  G06N3/084 ,  G06T3/4053 ,  G06V10/56 ,  G06V10/77

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for generating an output image. In one aspect, one of the methods includes generating the output image intensity value by intensity value according to a generation order of pixel-color channel pairs from the output image, comprising, for each particular generation order position in the generation order: generating a current output image representation of a current output image, processing the current output image representation using a decoder neural network to generate a probability distribution over possible intensity values for the pixel-color channel pair at the particular generation order position, wherein the decoder neural network includes one or more local masked self-attention sub-layers; and selecting an intensity value for the pixel-color channel pair at the particular generation order position using the probability distribution.

公开(公告)号：US12093829B2

公开(公告)日：2024-09-17

申请号：US18349089

申请日：2023-07-07

Applicant: Google LLC

Inventor： William Bradley Fedus ,  Barret Zoph ,  Noam M. Shazeer

IPC: G06N3/08 ,  G06N3/045 ,  G06N3/082

CPC classification number: G06N3/082 ,  G06N3/045

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing a machine learning task on a network input to generate a network output. In one aspect, one of the systems includes a neural network configured to perform the machine learning task, the neural network including one or more switch layers.

公开(公告)号：US12086713B2

公开(公告)日：2024-09-10

申请号：US17876451

申请日：2022-07-28

Applicant: Google LLC

Inventor： Daniel De Freitas Adiwardana ,  Noam M. Shazeer

IPC: G06N3/08 ,  G06F18/2113 ,  G06N20/00

CPC classification number: G06N3/08 ,  G06F18/2113 ,  G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for evaluating candidate output sequences using language model neural networks. In particular, an auto-regressive language model neural network is used to generate a candidate output sequence. The same auto-regressive language model neural network is used to evaluate the candidate output sequence to determine rating scores for each of one or more criteria. The rating score(s) are then used to determine whether to provide the candidate output sequence.

公开(公告)号：US20230419079A1

公开(公告)日：2023-12-28

申请号：US18244171

申请日：2023-09-08

Applicant: Google LLC

Inventor： Noam M. Shazeer ,  Azalia Mirhoseini ,  Krzysztof Stanislaw Maziarz

IPC: G06N3/045 ,  G06N3/08

CPC classification number: G06N3/045 ,  G06N3/08

Abstract: A system includes a neural network that includes a Mixture of Experts (MoE) subnetwork between a first neural network layer and a second neural network layer. The MoE subnetwork includes multiple expert neural networks. Each expert neural network is configured to process a first layer output generated by the first neural network layer to generate a respective expert output. The MoE subnetwork further includes a gating subsystem that selects, based on the first layer output, one or more of the expert neural networks and determine a respective weight for each selected expert neural network, provides the first layer output as input to each of the selected expert neural networks, combines the expert outputs generated by the selected expert neural networks in accordance with the weights for the selected expert neural networks to generate an MoE output, and provides the MoE output as input to the second neural network layer.