FRAMEWORK FOR COMPRESSION-AWARE TRAINING OF NEURAL NETWORKS

Methods and devices are provided for processing data using a neural network. Activations from a previous layer of the neural network are received by a layer of the neural network. Weighted values, to be applied to values of elements of the activations, are determined based on a spatial correlation o...

Full description

Saved in:
Bibliographic Details
Main Authors Colbert, Ian Charles, Saeedi, Mehdi, Amer, Ihab M. A
Format Patent
LanguageEnglish
Published 21.03.2024
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:Methods and devices are provided for processing data using a neural network. Activations from a previous layer of the neural network are received by a layer of the neural network. Weighted values, to be applied to values of elements of the activations, are determined based on a spatial correlation of the elements and a task error output by the layer. The weighted values are applied to the values of the elements and a combined error is determined based on the task error and the spatial correlation.
Bibliography:Application Number: US202217949082