公开(公告)号：US20240394545A1

公开(公告)日：2024-11-28

申请号：US18377368

申请日：2023-10-06

Applicant: Google LLC

Inventor： Julian Martin Eisenschlos ,  Xingchen Wan ,  Hootan Nakhost ,  Sercan Omer Arik ,  Ruoxi Sun ,  Hanjun Dai

IPC: G06N3/088 ,  G06N3/0455

Abstract: Aspects of the disclosure are directed to methods, systems, and computer readable media for universal self-adaptive prompting (USP), which includes an automatic prompt design approach specifically tailored for zero-shot learning, though still compatible with few-shot learning. To achieve universal prompting, USP categorizes a natural language processing (NLP) task into one of a plurality of possible task types and then uses a corresponding selector to select the most suitable queries and zero-shot model-generated responses as pseudo-demonstrations, thereby generalizing in-context learning to the zero-shot setup in a fully automated manner.

公开(公告)号：US20240378224A1

公开(公告)日：2024-11-14

申请号：US18654696

申请日：2024-05-03

Applicant: Google LLC

Inventor： Jinsung Yoon ,  Sercan Omer Arik

IPC: G06F16/33 ,  G06F16/332

Abstract: Aspects of the disclosed technology include techniques and mechanisms for customizing large language models (LLMs) for information retrieval (IR). For a plurality of (query, corpus) pairs, an IR adapter may generate embeddings and adapted embeddings associated with each of the query and the corpus. The IR adapter may analyze the adapted embeddings using a similarity function to determine the similarity between the adapted embeddings. The output of the similarity function may be used to determine a correlation between the query and the corpus, wherein the correlation may be fed back into the IR adapter to train an LLM.

公开(公告)号：US20240362212A1

公开(公告)日：2024-10-31

申请号：US18225277

申请日：2023-07-24

Applicant: Google LLC

Inventor： Ruoxi Sun ,  Sercan Omer Arik ,  Rajarishi Sinha ,  Hootan Nakhost ,  Hanjun Dai ,  Pengcheng Yin

IPC: G06F16/2452 ,  G06F16/242

CPC classification number: G06F16/24522 ,  G06F16/2433

Abstract: Aspects of the disclosure are directed to methods, systems, and non-transitory computer readable media for automatically generating queries on a database from natural language text using in-context learning to leverage zero-shot and few-shot adaptation capabilities of large language models (LLMs). The methods, systems, and non-transitory computer readable media can consider database information, employ execution based consistency decoding, and employ a mixture of prompts and/or LLMs.

公开(公告)号：US20240249204A1

公开(公告)日：2024-07-25

申请号：US18419476

申请日：2024-01-22

Applicant: Google LLC

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

IPC: G06N20/20

CPC classification number: G06N20/20

Abstract: A method includes obtaining a set of unlabeled test data samples and, for each respective initial training step, determining a first average output for each unlabeled test data sample using a deep ensemble. For each round of a plurality of rounds, the method includes selecting a subset of unlabeled test data samples based on the determined first average outputs, labeling each respective unlabeled in the subset of unlabeled test data samples, fine-tuning the deep ensemble model using the subset of labeled test data samples, and determining a second average output for each unlabeled test data sample using the fine-tuned deep ensemble model. The method also includes generating, using the set of unlabeled test data samples and the determined second average outputs, a pseudo-labeled set of training data samples. The method also includes training the deep ensemble model using the pseudo-labeled set of training data samples.

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：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：US20230325675A1

公开(公告)日：2023-10-12

申请号：US18333301

申请日：2023-06-12

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Jinsung Yoon ,  Tomas Pfister

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

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

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：US20230274154A1

公开(公告)日：2023-08-31

申请号：US18113267

申请日：2023-02-23

Applicant: Google LLC

Inventor： Jinsung Yoon ,  Sercan Omer Arik ,  Madeleine Richards Udell ,  Chun-Hao Chang

IPC: G06N3/09 ,  G06N3/088 ,  G06N3/0895

CPC classification number: G06N3/09 ,  G06N3/088 ,  G06N3/0895

Abstract: Aspects of the disclosure provide for interpretable anomaly detection using a generalized additive model (GAM) trained using unsupervised and supervised learning techniques. A GAM is adapted to detect anomalies using an anomaly detection partial identification (AD PID) loss function for handling noisy or heterogeneous features in model input. A semi-supervised data interpretable anomaly detection (DIAD) system can generate more accurate results over models trained for anomaly detection using strictly unsupervised techniques. In addition, output from the DIAD system includes explanations, for example as graphs or plots, of relatively important input features that contribute to the model output by different factors, providing interpretable results from which the DIAD system can be improved upon.

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

IPC: G06N5/04 ,  G06F11/34

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：US20220327328A1

公开(公告)日：2022-10-13

申请号：US17809798

申请日：2022-06-29

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Jinsung YOON ,  Tomas Join 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.