-
公开(公告)号:US11900235B1
公开(公告)日:2024-02-13
申请号:US17470716
申请日:2021-09-09
Applicant: Google LLC
Inventor: Andrew M. Dai , Quoc V. Le , David Ha
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing inputs using recurrent neural networks. One of the systems includes a main recurrent neural network comprising one or more recurrent neural network layers and a respective hyper recurrent neural network corresponding to each of the one or more recurrent neural network layers, wherein each hyper recurrent neural network is configured to, at each of a plurality of time steps: process the layer input at the time step to the corresponding recurrent neural network layer, the current layer hidden state of the corresponding recurrent neural network layer, and a current hypernetwork hidden state of the hyper recurrent neural network to generate an updated hypernetwork hidden state.
-
公开(公告)号:US11501168B2
公开(公告)日:2022-11-15
申请号:US16273041
申请日:2019-02-11
Applicant: Google LLC
Inventor: Andrew M. Dai , Quoc V. Le , Hoang Trieu Trinh , Thang Minh Luong
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for structuring and training a recurrent neural network. This describes a technique that improves the ability to capture long term dependencies in recurrent neural networks by adding an unsupervised auxiliary loss at one or more anchor points to the original objective. This auxiliary loss forces the network to either reconstruct previous events or predict next events in a sequence, making truncated backpropagation feasible for long sequences and also improving full backpropagation through time.
-
公开(公告)号:US20210034973A1
公开(公告)日:2021-02-04
申请号:US16943957
申请日:2020-07-30
Applicant: Google LLC
Inventor: Zhen Xu , Andrew M. Dai , Jonas Beachey Kemp , Luke Shekerjian Metz
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network. One of the methods includes training the neural network for one or more training steps in accordance with a current learning rate; generating a training dynamics observation characterizing the training of the trainee neural network on the one or more training steps; providing the training dynamics observation as input to a controller neural network that is configured to process the training dynamics observation to generate a controller output that defines an updated learning rate; obtaining as output from the controller neural network the controller output that defines the updated learning rate; and setting the learning rate to the updated learning rate.
-
公开(公告)号:US10770180B1
公开(公告)日:2020-09-08
申请号:US16712947
申请日:2019-12-12
Applicant: Google LLC
Inventor: Jonas Beachey Kemp , Andrew M. Dai , Alvin Rishi Rajkomar
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting future patient health using neural networks. One of the methods includes receiving electronic health record data for a patient; generating a respective observation embedding for each of the observations, comprising, for each clinical note: processing the sequence of tokens in the clinical note using a clinical note embedding LSTM to generate a respective token embedding for each of the tokens; and generating the observation embedding for the clinical note from the token embeddings; generating an embedded representation, comprising, for each time window: combining the observation embeddings of observations occurring during the time window to generate a patient record embedding; and processing the embedded representation of the electronic health record data using a prediction recurrent neural network to generate a neural network output that characterizes a future health status of the patient.
-
公开(公告)号:US20190251449A1
公开(公告)日:2019-08-15
申请号:US16273041
申请日:2019-02-11
Applicant: Google LLC
Inventor: Andrew M. Dai , Quoc V. Le , Hoang Trieu Trinh , Thang Minh Luong
CPC classification number: G06N3/084 , G06N3/0454 , G06N3/088
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for structuring and training a recurrent neural network. This describes a technique that improves the ability to capture long term dependencies in recurrent neural networks by adding an unsupervised auxiliary loss at one or more anchor points to the original objective. This auxiliary loss forces the network to either reconstruct previous events or predict next events in a sequence, making truncated backpropagation feasible for long sequences and also improving full backpropagation through time.
-
公开(公告)号:US20250037426A1
公开(公告)日:2025-01-30
申请号:US18716912
申请日:2022-12-09
Applicant: Google LLC
Inventor: Bowen Zhang , Jiahui Yu , Christopher Fifty , Wei Han , Andrew M. Dai , Ruoming Pang , Fei Sha
IPC: G06V10/764 , G06V10/774
Abstract: A method includes obtaining video datasets each including pairs of a training video and a ground-truth action classification of the training video. The method also includes generating an action recognition model that includes a shared encoder model and action classification heads. A number of the action classifications heads may be equal to a number of the video datasets, and each action classification head may be configured to, based on an output of the shared encoder model, classify training videos sampled from a corresponding video dataset. The method also includes determining, by the action recognition model and for each training video sampled from the video datasets, an inferred action classification. The method further includes determining a loss value based on the inferred action classifications and the ground-truth action classifications, and adjusting parameters of the action recognition model based on the loss value.
-
公开(公告)号:US20240112027A1
公开(公告)日:2024-04-04
申请号:US18477546
申请日:2023-09-28
Applicant: Google LLC
Inventor: Yanqi Zhou , Yanping Huang , Yifeng Lu , Andrew M. Dai , Siamak Shakeri , Zhifeng Chen , James Laudon , Quoc V. Le , Da Huang , Nan Du , David Richard So , Daiyi Peng , Yingwei Cui , Jeffrey Adgate Dean , Chang Lan
IPC: G06N3/08
CPC classification number: G06N3/08
Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for performing neural architecture search for machine learning models. In one aspect, a method comprises receiving training data for a machine learning, generating a plurality of candidate neural networks for performing the machine learning task, wherein each candidate neural network comprises a plurality of instances of a layer block composed of a plurality of layers, for each candidate neural network, selecting a respective type for each of the plurality of layers from a set of layer types that comprises, training the candidate neural network and evaluating performance scores for the trained candidate neural networks as applied to the machine learning task, and determining a final neural network for performing the machine learning task based at least on the performance scores for the candidate neural networks.
-
公开(公告)号:US11200492B1
公开(公告)日:2021-12-14
申请号:US16735453
申请日:2020-01-06
Applicant: Google LLC
Inventor: Andrew M. Dai , Quoc V. Le
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a document classification neural network. One of the methods includes training an autoencoder neural network to autoencode input documents, wherein the autoencoder neural network comprises the one or more LSTM neural network layers and an autoencoder output layer, and wherein training the autoencoder neural network comprises determining pre-trained values of the parameters of the one or more LSTM neural network layers from initial values of the parameters of the one or more LSTM neural network layers; and training the document classification neural network on a plurality of training documents to determine trained values of the parameters of the one or more LSTM neural network layers from the pre-trained values of the parameters of the one or more LSTM neural network layers.
-
公开(公告)号:US20240378427A1
公开(公告)日:2024-11-14
申请号:US18661499
申请日:2024-05-10
Applicant: Google LLC
Inventor: Slav Petrov , Yonghui Wu , Andrew M. Dai , David Richard So , Dmitry Lepikhin , Erica Ann Moreira , Gaurav Mishra , Jonathan Hudson Clark , Maxim Krikun , Melvin Jose Johnson Premkumar , Nan Du , Orhan Firat , Rohan Anil , Siamak Shakeri , Xavier Garcia , Yanping Huang , Yong Cheng , Yuanzhong Xu , Yujing Zhang , Zachary Alexander Nado , Eric Jun Jie Ni , Kefan Xiao , Vladimir Feinberg , Jin Young Sohn , Aurko Roy
IPC: G06N3/0475 , G06F40/284
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training a neural network to perform any one or more of a variety of machine learning tasks. For example, the neural network can be configured as a generative neural network, e.g., an autoregressive generative neural network.
-
10.
公开(公告)号:US20230334306A1
公开(公告)日:2023-10-19
申请号:US16794087
申请日:2020-02-18
Applicant: Google LLC
Inventor: Kun Zhang , Andrew M. Dai , Yuan Xue , Alvin Rishi Rajkomar , Gerardo Flores
Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for predicting future patient health using a recurrent neural network. In particular, at each time step, a network input for the time step is processed using a recurrent neural network to update a hidden state of the recurrent neural network. Specifically, the hidden state of the recurrent neural network is partitioned into a plurality of partitions and the plurality of partitions comprises a respective partition for each of a plurality of possible observational features.
-
-
-
-
-
-
-
-
-