-
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:US20250036886A1
公开(公告)日:2025-01-30
申请号:US18766812
申请日:2024-07-09
Applicant: Google LLC
Inventor: Chen-Yu Lee , Alexander Ratner , Tomas Pfister , Chun-Liang Li , Yasuhisa Fujii , Ranjay Krishna , Cheng-Yu Hsieh , Si-An Chen
IPC: G06F40/40 , G06N3/0475
Abstract: Using a large language model to comply with a user request. The large language model receives tool documentation for each of one or more tools, and analyzes the tool documentation for each of the one or more tools to determine, for each tool, one or more tasks that the tool is operable to perform. Upon receiving a request from a user, the large language model generates a plan for complying with the request by using one or more of the tools, the plan including performance of one or more of the tasks.
-
公开(公告)号:US20240249192A1
公开(公告)日:2024-07-25
申请号:US18417556
申请日:2024-01-19
Applicant: Google LLC
Inventor: Sercan Omer Arik , Si-An Chen , Nathanael Christian Yoder , Chun-Liang Li
IPC: G06N20/00
CPC classification number: G06N20/00
Abstract: The present disclosure provides an architecture for time series forecasting. The architecture is based on multi-layer perceptrons (MLPs), which involve stacking linear models with non-linearities between them. In this architecture, the time-domain MLPs and feature-domain MLPs are used to perform both time-domain and feature-domain operations in a sequential manner, alternating between them. In some examples, auxiliary data is used as input, in addition to historical data. The auxiliary data can include known future data points, as well as static information that does not vary with time. The alternation of time-domain and feature-domain operations using linear models allows the architecture to learn temporal patterns while leveraging cross-variate information to generate more accurate time series forecasts.
-
公开(公告)号:US20220391724A1
公开(公告)日:2022-12-08
申请号:US17825788
申请日:2022-05-26
Applicant: Google LLC
Inventor: Jinsung Yoon , Kihyuk Sohn , Chun-Liang Li , Sercan Omer Arik
Abstract: Aspects of the disclosure provide for methods, systems, and apparatus, including computer-readable storage media, for anomaly detection using a machine learning framework trained entirely on unlabeled training data including both anomalous and non-anomalous training examples. A self-supervised one-class classifier (STOC) refines the training data to exclude anomalous training examples, using an ensemble of machine learning models. The ensemble of models are retrained on the refined training data. The STOC can also use the refined training data to train a representation learning model to generate one or more feature values for each training example, which can be processed by the trained ensemble of models and eventually used for training an output classifier model to predict whether input data is indicative of anomalous or non-anomalous data.
-
公开(公告)号:US20240354504A1
公开(公告)日:2024-10-24
申请号:US18684557
申请日:2021-08-25
Applicant: Google LLC
Inventor: Chen-Yu Lee , Chun-Liang Li , Timothy Dozat , Vincent Perot , Guolong Su , Nan Hua , Joshua Ainslie , Renshen Wang , Yasuhisa Fujii , Tomas Pfister
IPC: G06F40/284 , G06V30/10 , G06V30/416
CPC classification number: G06F40/284 , G06V30/10 , G06V30/416
Abstract: Systems and methods for providing a structure-aware sequence model that can interpret a document's text without first inferring the proper reading order of the document. In some examples, the model may use a graph convolutional network to generate contextualized “supertoken” embeddings for each token, which are then fed to a transformer that employs a sparse attention paradigm in which attention weights for at least some supertokens are modified based on differences between predicted and actual values of the order and distance between the attender and attendee supertokens.
-
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.
-
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
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.
-
-
-
-
-
-
-