公开(公告)号：US20240249080A1

公开(公告)日：2024-07-25

申请号：US18128450

申请日：2023-03-30

Applicant: Google LLC

Inventor： Ruoxi Sun ,  Xingchen Wan ,  Hanjun Dai ,  Sercan Omer Arik ,  Tomas Pfister

IPC: G06F40/40 ,  G06F16/33

CPC classification number: G06F40/40 ,  G06F16/3344

Abstract: Aspects of the disclosure are directed to automatically selecting examples in a prompt for an LLM to demonstrate how to perform tasks. Aspects of the disclosure can select and build a set of examples from LLM zero-shot outputs via predetermined criteria that can combine consistency, diversity, and repetition. In the zero-shot setting for three different LLMs, using only LLM predictions, aspects of the disclosure can improve performance up to 15% compared to zero-shot baselines and can match or exceed few-shot base-lines for a range of reasoning tasks.

公开(公告)号：US20230110117A1

公开(公告)日：2023-04-13

申请号：US17954978

申请日：2022-09-28

Applicant: Google LLC

Inventor： Sercan Omer Arik ,  Nathanael Christian Yoder ,  Tomas Pfister

IPC: G06N3/04 ,  G06N3/08

Abstract: Aspects of the disclosure provide for self-adapting forecasting (SAF) during the training and execution of machine learning models trained for multi-horizon forecasting on time-series data. The distribution of time-series data can shift over different periods of time. A deep neural network and other types of machine learning models are trained assuming that training data is independent and identically distributed (i.i.d.). With a computer system configured to execute SAF, the system can, at inference time, update a trained encoder to generate an encoded representation of time-series data capturing features characterizing the current distribution of the input time-series data. The updated encoded representation can be fed into a decoder trained to generate a multi-horizon forecast based on the updated encoded representation of the time-series data. At each instance of inference, the base weights of a trained model can be reused and updated to generate an updated encoded representation for that instance.

公开(公告)号：US20230018125A1

公开(公告)日：2023-01-19

申请号：US17782865

申请日：2020-11-25

Applicant: Google LLC

Inventor： Si Jie Bryan Lim ,  Sercan Omer Arik ,  Nicolas Loeff ,  Tomas Pfister

IPC: G06N3/08

Abstract: Methods, systems, and apparatus, including computer storage media, for performing multi-horizon forecasting on time-series data. A method includes determining short-term temporal characteristics for respective forecasting horizons of one or more time-steps. The determining can include generating, using RNN encoders, encoder vectors based on static covariates, and time-varying input data; and predicting using one or more RNN decoders, a short-term pattern for a respective future time period. The method can also include capturing long-term temporal characteristics for the respective forecasting horizons based on the static covariates, the time-varying input data captured during the respective past time-periods, and the time-varying known future input data.

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.