公开(公告)号：US20210089870A1

公开(公告)日：2021-03-25

申请号：US17026145

申请日：2020-09-18

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Jinsung Yoon ,  Tomas Jon Pfister

IPC: G06N3/04 ,  G06N3/08 ,  G06F17/16

Abstract: A method includes obtaining a set of training samples. During each of a plurality of training iterations, the method also includes sampling a batch of training samples from the set of training samples. The method includes, for each training sample in the batch of training samples, determining, using a data value estimator, a selection probability. The selection probability for the training sample is based on estimator parameter values of the data value estimator. The method also includes selecting, based on the selection probabilities of each training sample, a subset of training samples from the batch of training samples, and determining, using a predictor model with the subset of training samples, performance measurements. The method also includes adjusting model parameter values of the predictor model based on the performance measurements, and updating the estimator parameter values of the data value estimator based on the performance measurements.

公开(公告)号：US20210034976A1

公开(公告)日：2021-02-04

申请号：US16945880

申请日：2020-08-02

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Tomas Jon Pfister ,  Linchao Zhu

IPC: G06N3/08 ,  G06N3/04

Abstract: A method includes receiving a source data set and a target data set and identifying a loss function for a deep learning model based on the source data set and the target data set. The loss function includes encoder weights, source classifier layer weights, target classifier layer weights, coefficients, and a policy weight. During a first phase of each of a plurality of learning iterations for a learning to transfer learn (L2TL) architecture, the method also includes: applying gradient decent-based optimization to learn the encoder weights, the source classifier layer weights, and the target classifier weights that minimize the loss function; and determining the coefficients by sampling actions of a policy model. During a second phase of each of the plurality of learning iterations, determining the policy weight that maximizes an evaluation metric.

公开(公告)号：US20240054345A1

公开(公告)日：2024-02-15

申请号：US18455182

申请日：2023-08-24

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Tomas Jon Pfister ,  Linchao Zhu

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04

Abstract: A method includes receiving a source data set and a target data set and identifying a loss function for a deep learning model based on the source data set and the target data set. The loss function includes encoder weights, source classifier layer weights, target classifier layer weights, coefficients, and a policy weight. During a first phase of each of a plurality of learning iterations for a learning to transfer learn (L2TL) architecture, the method also includes: applying gradient decent-based optimization to learn the encoder weights, the source classifier layer weights, and the target classifier weights that minimize the loss function; and determining the coefficients by sampling actions of a policy model. During a second phase of each of the plurality of learning iterations, determining the policy weight that maximizes an evaluation metric.

公开(公告)号：US11205096B2

公开(公告)日：2021-12-21

申请号：US16688773

申请日：2019-11-19

Applicant: Google LLC

Inventor： Rui Zhang ,  Jia Li ,  Tomas Jon Pfister

IPC: G06K9/62 ,  G06N3/04 ,  G06N3/08

Abstract: A computer-implemented method for training a forward generator neural network G to translate a source image in a source domain X to a corresponding target image in a target domain Y is described. The method includes: obtaining a source training dataset sampled from the source domain X according to a source domain distribution, the source training dataset comprising a plurality of source training images; obtaining a target training dataset sampled from the target domain Y according to a target domain distribution, the target training dataset comprising a plurality of target training images; for each of the source training images in the source training dataset, translating, using the forward generator neural network G, each source training image to a respective translated target image in the target domain Y according to current values of forward generator parameters of the forward generator neural network G; for each of the target training images in the target training dataset, translating, using a backward generator neural network F, each target training image to a respective translated source image in the source domain X according to current values of backward generator parameters of the backward generator neural network F; and training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function, wherein the objective function comprises a harmonic loss component that ensures (i) similarity-consistency between patches in each source training image and patches in its corresponding translated target image, and (ii) similarity-consistency between patches in each target training image and patches in its corresponding translated source image.

公开(公告)号：US20210089828A1

公开(公告)日：2021-03-25

申请号：US17030316

申请日：2020-09-23

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Jinsung Yoon ,  Tomas Jon Pfister

IPC: G06K9/62 ,  G06N3/02

Abstract: A method for training a locally interpretable model includes obtaining a set of training samples and training a black-box model using the set of training samples. The method also includes generating, using the trained black-box model and the set of training samples, a set of auxiliary training samples and training a baseline interpretable model using the set of auxiliary training samples. The method also includes training, using the set of auxiliary training samples and baseline interpretable model, an instance-wise weight estimator model. For each auxiliary training sample in the set of auxiliary training samples, the method also includes determining, using the trained instance-wise weight estimator model, a selection probability for the auxiliary training sample. The method also includes selecting, based on the selection probabilities, a subset of auxiliary training samples and training the locally interpretable model using the subset of auxiliary training samples.

公开(公告)号：US20200160113A1

公开(公告)日：2020-05-21

申请号：US16688773

申请日：2019-11-19

Applicant: Google LLC

Inventor： Rui Zhang ,  Jia Li ,  Tomas Jon Pfister

IPC: G06K9/62 ,  G06N3/04

Abstract: A computer-implemented method for training a forward generator neural network G to translate a source image in a source domain X to a corresponding target image in a target domain Y is described. The method includes: obtaining a source training dataset sampled from the source domain X according to a source domain distribution, the source training dataset comprising a plurality of source training images; obtaining a target training dataset sampled from the target domain Y according to a target domain distribution, the target training dataset comprising a plurality of target training images; for each of the source training images in the source training dataset, translating, using the forward generator neural network G, each source training image to a respective translated target image in the target domain Y according to current values of forward generator parameters of the forward generator neural network G; for each of the target training images in the target training dataset, translating, using a backward generator neural network F, each target training image to a respective translated source image in the source domain X according to current values of backward generator parameters of the backward generator neural network F; and training the forward generator neural network G jointly with the backward generator neural network F by adjusting the current values of the forward generator parameters and the backward generator parameters to optimize an objective function, wherein the objective function comprises a harmonic loss component that ensures (i) similarity-consistency between patches in each source training image and patches in its corresponding translated target image, and (ii) similarity-consistency between patches in each target training image and patches in its corresponding translated source image.

公开(公告)号：US20240144005A1

公开(公告)日：2024-05-02

申请号：US18404881

申请日：2024-01-04

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Tomas Jon Pfister

IPC: G06N3/08 ,  G06N3/04

CPC classification number: G06N3/08 ,  G06N3/04

Abstract: A method of interpreting tabular data includes receiving, at a deep tabular data learning network (TabNet) executing on data processing hardware, a set of features. For each of multiple sequential processing steps, the method also includes: selecting, using a sparse mask of the TabNet, a subset of relevant features of the set of features; processing using a feature transformer of the TabNet, the subset of relevant features to generate a decision step output and information for a next processing step in the multiple sequential processing steps; and providing the information to the next processing step. The method also includes determining a final decision output by aggregating the decision step outputs generated for the multiple sequential processing steps.

公开(公告)号：US11823058B2

公开(公告)日：2023-11-21

申请号：US17026145

申请日：2020-09-18

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Jinsung Yoon ,  Tomas Jon Pfister

IPC: G06N3/04 ,  G06N3/08 ,  G06N3/084 ,  G06F17/16 ,  G06N3/047 ,  G06N3/092

CPC classification number: G06N3/084 ,  G06F17/16 ,  G06N3/047 ,  G06N3/08 ,  G06N3/092

Abstract: A method includes obtaining a set of training samples. During each of a plurality of training iterations, the method also includes sampling a batch of training samples from the set of training samples. The method includes, for each training sample in the batch of training samples, determining, using a data value estimator, a selection probability. The selection probability for the training sample is based on estimator parameter values of the data value estimator. The method also includes selecting, based on the selection probabilities of each training sample, a subset of training samples from the batch of training samples, and determining, using a predictor model with the subset of training samples, performance measurements. The method also includes adjusting model parameter values of the predictor model based on the performance measurements, and updating the estimator parameter values of the data value estimator based on the performance measurements.

公开(公告)号：US20230153980A1

公开(公告)日：2023-05-18

申请号：US18054524

申请日：2022-11-10

Applicant: Google LLC

Inventor： Kihyuk Sohn ,  Jinsung Yoon ,  Chun-Liang Li ,  Tomas Jon Pfister ,  Chen-Yu Lee

IPC: G06T7/00 ,  G06V10/762

CPC classification number: G06T7/0004 ,  G06V10/7625 ,  G06V10/7635 ,  G06T2207/20081 ,  G06V10/764

Abstract: A computer-implemented method includes receiving an anomaly clustering request that requests data processing hardware to assign each image of a plurality of images into one of a plurality of groups. The method also includes obtaining a plurality of images. For each respective image, the method includes extracting a respective set of patch embeddings from the respective image, determining a distance between the respective set of patch embeddings and each other set of patch embeddings, and assigning the respective image into one of the plurality of groups using the distances between the respective set of patch embeddings and each other set of patch embeddings.

公开(公告)号：US20230120894A1

公开(公告)日：2023-04-20

申请号：US18045722

申请日：2022-10-11

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Chen Xing ,  Zizhao Zhang ,  Tomas Jon Pfister

IPC: G06N3/08 ,  G06N3/04 ,  G06F18/214 ,  G06F18/2413 ,  G06F18/2431

Abstract: A method includes receiving a training data set including a plurality of training data subsets. From two or more training data subsets in the training data set, the method includes selecting a support set of training examples and a query set of training examples. The method includes determining, using the classification model, a centroid value for each respective class. For each training example in the query set of training examples, the method includes generating, using the classification model, a query encoding, determining a class distance measure, determining a ground-truth distance, and updating parameters of the classification model. For each training example in the query set of training examples identified as being misclassified, the method further includes generating a standard deviation value, sampling a new query, and updating parameters of the confidence model based on the new query encoding.