LOW RANK MATRIX COMPRESSION

In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer. Other embodiments are also disclosed and claim...

Full description

Saved in:
Bibliographic Details
Main Authors Bar-On, Tomer, Cohen, Ehud, Novik, Gal, Sarel, Uzi, Fais, Yaniv, Leibovich, Gal, Dreyfuss, Jeremie, Faivishevsky, Lev, Schwartz, Tomer, Shadmiy, Yahav, Subag, Jacob, Armon, Amitai
Format Patent
LanguageEnglish
Published 05.10.2023
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC COMMUNICATION TECHNIQUE
ELECTRICITY
IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
PHYSICS
PICTORIAL COMMUNICATION, e.g. TELEVISION
Online AccessGet full text

Cover

More Information
Summary:In an example, an apparatus comprises logic, at least partially including hardware logic, to implement a lossy compression algorithm which utilizes a data transform and quantization process to compress data in a convolutional neural network (CNN) layer. Other embodiments are also disclosed and claimed.
Bibliography:Application Number: US202318191565