Gangotree Chakma, Mark E. Dean, Garrett S. Rose, Karsten Beckmann, H. Manem and Nathaniel Cady

November, 2016

International Workshop on Post-Moore's Era Supercomputing (PMES)

https://sites.google.com/site/2016pmes/

View Article

Abstract

Power and precise scaling are significant restraining elements to advancements in computing. This paper presents a power efficient memristive device technology in the design of a neuromorphic architectural model that promises to overcome many of the performance limitations of conventional Von Neumann systems. The resulting memristive Dynamic Adaptive Neural Network Array (mrDANNA) addresses contemporary application challenges while also enabling continued performance scaling. The mrDANNA system is a mixed-mode neuromorphic computing system built with reconfigurable structure, dynamic adaptation, low-power operation, and is well suited for processing spatio-temporal data. This work is specifically based on a HfO₂ memristor device, experimental results for which are presented in this paper. Proof-of-concept simulation results for a mrDANNA pattern recognition network are also presented showing high accuracy for recognizing basic shapes.

Citation Information

Text

author     G. Chakma and Mark E. Dean and G. S. Rose and K. Beckmann and H. Manem and N. Cady
title      A Hafnium-Oxide Memristive Dynamic Adaptive Neural Network Array
booktitle  International Workshop on Post-Moore's Era Supercomputing (PMES)
month      November
year       2016
address    Salt Lake City, UT
where      https://sites.google.com/site/2016pmes/

Bibtex

@INPROCEEDINGS{cdr:16:hom,
    author = "G. Chakma and Mark E. Dean and G. S. Rose and K. Beckmann and H. Manem and N. Cady",
    title = "A Hafnium-Oxide Memristive Dynamic Adaptive Neural Network Array",
    booktitle = "International Workshop on Post-Moore's Era Supercomputing (PMES)",
    month = "November",
    year = "2016",
    address = "Salt Lake City, UT",
    where = "https://sites.google.com/site/2016pmes/"
}