公开(公告)号：US20240119366A1

公开(公告)日：2024-04-11

申请号：US18477525

申请日：2023-09-28

Applicant: Google LLC

Inventor： Matthew Jones ,  Michael Curtis Mozer

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for online training of machine learning models predicting time-series data. In one aspect, a method comprises training a machine learning model having a plurality of weights by maintaining weight data, specifying a plurality of sub-weights for each of the plurality of weights and covariance data that estimates the joint uncertainty between the sub-weights, and, at each of a plurality of time steps, receiving model inputs, processing the model inputs using the weight data to generate corresponding model outputs, receiving corresponding ground truth outputs, and updating the weight data using the corresponding ground truth outputs.

公开(公告)号：US20220253695A1

公开(公告)日：2022-08-11

申请号：US17560139

申请日：2021-12-22

Applicant: Google LLC

Inventor： Michael Curtis Mozer ,  Michael Louis Iuzzolino ,  Samuel Bengio

IPC: G06N3/08

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing a network input using a parallel cascaded neural network that includes multiple neural network blocks that each have a skip connection and a propagation delay. Methods, systems, and apparatus, including computer programs encoded on computer storage media, for training parallel cascaded neural networks using temporal difference learning are also described.