Defect consideratons for robust sparse coding using memristor arrays

The performance of a memristor network with defects is investigated on a sparse coding task. It was found that moderate levels SA0 faults do not significantly impact algorithm performance, while SA1 faults effectively reduce dictionary size.

Saved in:
Bibliographic Details
Published in:IEEE International Symposium on Nanoscale Architectures pp. 137 - 138
Main Authors: Sheridan, Patrick, Lu, Wei D.
Format: Conference Proceeding
Language:English
Published: IEEE 01.07.2015
Subjects:
crossbar
Dictionaries
Electrodes
Encoding
fault tolerance
Memristor
Memristors
Neurons
Performance evaluation
sparse coding
Training
ISSN:2327-8218
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The performance of a memristor network with defects is investigated on a sparse coding task. It was found that moderate levels SA0 faults do not significantly impact algorithm performance, while SA1 faults effectively reduce dictionary size.
ISSN:2327-8218
DOI:10.1109/NANOARCH.2015.7180600