← All patents

US20230244949A1

Methods and systems to train neural networks

University of Texas System

Abstract

A computer-implemented technique for training an artificial neural network is disclosed. The technique includes obtaining a training sample for training the artificial neural network; determining multiple sub concepts within the training sample; processing the sub concepts to obtain differential …

University
University of Texas System
Assignee
The Board Of Regents Of The University Of Texas System
Inventor
Milo M. LIN
Priority date
February 24, 2020
Filing date
February 24, 2021
Publication date
August 03, 2023
Language
en
Metadata fetched
August 29, 2026 00:31