Accelerated training for neural network models

Apparatuses, systems, and techniques to accelerate training of one or more neural networks. In at least one embodiment, training values for individual nodes in a first neural network are estimated using a second neural network or other estimation technique in order to decrease time required to train...

Full description

Saved in:
Bibliographic Details
Main Authors Christopher Ian Schneider, Andrew James Woodard, Benjemin Thomas Waine, Amy Leigh Rose
Format Patent
LanguageEnglish
Published 27.04.2022
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Apparatuses, systems, and techniques to accelerate training of one or more neural networks. In at least one embodiment, training values for individual nodes in a first neural network are estimated using a second neural network or other estimation technique in order to decrease time required to train the first neural network.
Bibliography:Application Number: GB20220000838