公开(公告)号：US12125265B2

公开(公告)日：2024-10-22

申请号：US17809798

申请日：2022-06-29

Applicant: Google LLC

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

IPC: G06V10/774 ,  G06F18/21 ,  G06F18/2115 ,  G06F18/214 ,  G06N3/006 ,  G06N3/02 ,  G06N3/045 ,  G06N3/084 ,  G06N3/088 ,  G06N5/01 ,  G06N5/045 ,  G06N7/01 ,  G06N20/20 ,  G06V30/19

CPC classification number: G06V10/774 ,  G06F18/2115 ,  G06F18/2148 ,  G06F18/2193 ,  G06N3/006 ,  G06N3/02 ,  G06N3/045 ,  G06N3/084 ,  G06N3/088 ,  G06N5/045 ,  G06N7/01 ,  G06V30/19147 ,  G06N5/01 ,  G06N20/20

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：US20220245451A1

公开(公告)日：2022-08-04

申请号：US17591845

申请日：2022-02-03

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Sungyong Seo ,  Minho Jin ,  Jinsung Yoon ,  Tomas Pfister

IPC: G06N3/08 ,  G06N3/04

Abstract: The present disclosure provides a method to integrate prior knowledge (referred to as rules) into deep learning in a way that can be controllable at inference without retraining or tuning the model. Deep Neural Networks with Controllable Rule Representations (DNN-CRR) incorporate a rule encoder into the model architecture, which is coupled with a corresponding rule-based objective for enabling a shared representation to be used in decision making by learning both the original task and the rule. DNN-CRR is agnostic to data type and encoder architecture and can be applied to any kind of rule defined for inputs and/or outputs. In real-world domains where incorporating rules is critical, such as prediction tasks in Physics, Retail, and Healthcare.

公开(公告)号：US11941084B2

公开(公告)日：2024-03-26

申请号：US17454605

申请日：2021-11-11

Applicant: Google LLC

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

IPC: G06F18/214 ,  G06N3/08 ,  G06V10/22 ,  G06V10/774 ,  G06V10/82

CPC classification number: G06F18/2155 ,  G06N3/08 ,  G06V10/22

Abstract: A method for training a machine learning model includes obtaining a set of training samples. For each training sample in the set of training samples, during each of one or more training iterations, the method includes cropping the training sample to generate a first cropped image, cropping the training sample to generate a second cropped image that is different than the first cropped image, and duplicating a first portion of the second cropped image. The method also includes overlaying the duplicated first portion of the second cropped image on a second portion of the second cropped image to form an augmented second cropped image. The first portion is different than the second portion. The method also includes training the machine learning model with the first cropped image and the augmented second cropped image.

公开(公告)号：US20220156521A1

公开(公告)日：2022-05-19

申请号：US17454605

申请日：2021-11-11

Applicant: Google LLC

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

IPC: G06K9/62 ,  G06K9/20 ,  G06N3/08

Abstract: A method for training a machine learning model includes obtaining a set of training samples. For each training sample in the set of training samples, during each of one or more training iterations, the method includes cropping the training sample to generate a first cropped image, cropping the training sample to generate a second cropped image that is different than the first cropped image, and duplicating a first portion of the second cropped image. The method also includes overlaying the duplicated first portion of the second cropped image on a second portion of the second cropped image to form an augmented second cropped image. The first portion is different than the second portion. The method also includes training the machine learning model with the first cropped image and the augmented second cropped image.

公开(公告)号：US20240428015A1

公开(公告)日：2024-12-26

申请号：US18386343

申请日：2023-11-02

Applicant: Google LLC

Inventor： Jinsung Yoon ,  Jiefeng Chen ,  Sayna Ebrahimi ,  Sercan Omer Arik

IPC: G06F40/40

Abstract: Aspects of the disclosure are directed to methods, systems, and computer readable media for adaptation with self-evaluation to improve selective prediction in large language models (LLMs), generally referred to as ASPIRE. ASPIRE includes training LLMs on a portion of training data from a question answering task to learn self-evaluation, e.g., learn to distinguish whether a generated answer is correct or not. ASPIRE further includes a selection score that combines a likelihood of that generated answer is correct with a self-evaluation score for selective prediction. ASPIRE demonstrates improved selective prediction performance with less computational cost.

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：US12106223B2

公开(公告)日：2024-10-01

申请号：US18333301

申请日：2023-06-12

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Jinsung Yoon ,  Tomas Pfister

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

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

Abstract: A method includes obtaining a batch of training samples. For each particular training sample in the batch of training samples, the method includes generating, using a data value estimator model and the particular training sample, a corresponding predicted value of the particular training sample when used to train a machine learning model. The method includes selecting, based on the corresponding predicted values, a subset of the batch of training samples. For each particular training sample in the subset of the batch of training samples, the method includes determining, using the machine learning model and the particular training sample, a corresponding prediction performance measurement. The method includes adjusting one or more estimator parameter values of the data value estimator model based on the corresponding prediction performance measurements.

公开(公告)号：US20240185043A1

公开(公告)日：2024-06-06

申请号：US18389010

申请日：2023-11-13

Applicant: Google LLC

Inventor： Jinsung Yoon ,  Michel Jonathan Mizrahi ,  Nahid Farhady Ghalaty ,  Thomas Dunn Henry Jarvinen ,  Ashwin Sura Ravi ,  Peter Robert Brune ,  Fanyu Kong ,  David Roger Anderson ,  George Lee ,  Farhana Bandukwala ,  Eliezer Yosef Kanal ,  Sercan Omer Arik ,  Tomas Pfister

IPC: G06N3/0475 ,  G06N3/0455

CPC classification number: G06N3/0475 ,  G06N3/0455

Abstract: The present disclosure provides a generative modeling framework for generating highly realistic and privacy preserving synthetic records for heterogenous time-series data, such as electronic health record data, financial data, etc. The generative modeling framework is based on a two-stage model that includes sequential encoder-decoder networks and generative adversarial networks (GANs).

公开(公告)号：US20230237260A1

公开(公告)日：2023-07-27

申请号：US18150277

申请日：2023-01-05

Applicant: Google LLC

Inventor： Jinsung Yoon ,  Kihyuk Sohn ,  Chun-Liang Li ,  Sercan Omer Arik

IPC: G06F40/216 ,  G06N5/022

CPC classification number: G06F40/216 ,  G06N5/022

Abstract: Aspects of the disclosure are directed to a Semi-supervised Pseudo-labeler Anomaly Detection with Ensembling (SPADE) framework that is not limited by the assumption that labeled and unlabeled data come from the same distribution. SPADE utilizes an ensemble of one-class classifiers as the pseudo-labeler to improve the robustness of pseudo-labeling with distribution mismatch. Partial matching automatically selects critical hyper-parameters for pseudo-labeling without validation data, which is crucial with a limited amount of labeled data.