A 218 GOPS neural network accelerator based on a novel cost-efficient surrogate gradient scheme for pattern classification.

Saved in:
Bibliographic Details
Title: A 218 GOPS neural network accelerator based on a novel cost-efficient surrogate gradient scheme for pattern classification.
Authors: Siddique, Ali1,2, Iqbal, Muhammad Azhar1,3, azhar.iqbal@lancaster.ac.uk, Aleem, Muhammad4, Islam, Muhammad Arshad4
Source: Microprocessors & Microsystems; Jun2023, Vol. 99, pN.PAG-N.PAG, 1p
Database: Applied Science & Technology Source
Description
ISSN:01419331
DOI:10.1016/j.micpro.2023.104831