Title :
Defect consideratons for robust sparse coding using memristor arrays
Author :
Sheridan, Patrick ; Lu, Wei D.
Author_Institution :
Dept. of Electr. Eng. & Comput. Sci., Univ. of Michigan, Ann Arbor, MI, USA
Abstract :
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.
Keywords :
image coding; image sampling; memristor circuits; neural nets; SA0 faults; SA1 faults; dictionary size; memristor arrays; memristor network; robust sparse coding; Dictionaries; Electrodes; Encoding; Memristors; Neurons; Performance evaluation; Training; Memristor; crossbar; fault tolerance; sparse coding;
Conference_Titel :
Nanoscale Architectures (NANOARCH), 2015 IEEE/ACM International Symposium on
Conference_Location :
Boston, MA
DOI :
10.1109/NANOARCH.2015.7180600
