Neurophysics-inspired parallel architecture with resistive crosspoint array for dictionary learning

Deepak Kadetotad, Zihan Xu, Abinash Mohanty, Pai Yu Chen, Binbin Lin, Jieping Ye, Sarma Vrudhula, Shimeng Yu, Yu Cao, Jae Sun Seo

Research output: Chapter in Book/Report/Conference proceedingConference contribution

10 Scopus citations

Abstract

This paper proposes a parallel architecture with resistive crosspoint array. The design of its two essential operations, Read and Write, is inspired by the biophysical behavior of a neural system, such as integrate-and-fire and time-dependent synaptic plasticity. The proposed hardware consists of an array with resistive random access memory (RRAM) and CMOS peripheral circuits, which perform matrix product and dictionary update in a fully parallel fashion, at the speed that is independent of the matrix dimension. The entire system is implemented in 65nm CMOS technology with RRAM to realize high-speed unsupervised dictionary learning. As compared to state-of-the-art software approach, it achieves more than 3000X speedup, enabling real-time feature extraction on a single chip.

Original languageEnglish (US)
Title of host publicationIEEE 2014 Biomedical Circuits and Systems Conference, BioCAS 2014 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages536-539
Number of pages4
ISBN (Electronic)9781479923465
DOIs
StatePublished - Dec 9 2014
Externally publishedYes
Event10th IEEE Biomedical Circuits and Systems Conference, BioCAS 2014 - Lausanne, Switzerland
Duration: Oct 22 2014Oct 24 2014

Publication series

NameIEEE 2014 Biomedical Circuits and Systems Conference, BioCAS 2014 - Proceedings

Conference

Conference10th IEEE Biomedical Circuits and Systems Conference, BioCAS 2014
Country/TerritorySwitzerland
CityLausanne
Period10/22/1410/24/14

Bibliographical note

Publisher Copyright:
© 2014 IEEE.

Fingerprint

Dive into the research topics of 'Neurophysics-inspired parallel architecture with resistive crosspoint array for dictionary learning'. Together they form a unique fingerprint.

Cite this