Title

Low-Energy Deep Belief Networks Using Intrinsic Sigmoidal Spintronic-Based Probabilistic Neurons

Abstract

A low-energy hardware implementation of deep belief network (DBN) architecture is developed using near-zero energy barrier probabilistic spin logic devices (p-bits), which are modeled to realize an intrinsic sigmoidal activation function. A CMOS/spin based weighted array structure is designed to implement a restricted Boltzmann machine (RBM). Device-level simulations based on precise physics relations are used to validate the sigmoidal relation between the output probability of a p-bit and its input currents. Characteristics of the resistive networks and p-bits are modeled in SPICE to perform a circuit-level simulation investigating the performance, area, and power consumption tradeoffs of the weighted array. In the application-level simulation, a DBN is implemented in MATLAB for digit recognition using the extracted device and circuit behavioral models. The MNIST data set is used to assess the accuracy of the DBN using 5,000 training images for five distinct network topologies. The results indicate that a baseline error rate of 36.8% for a 784×10 DBN trained by 100 samples can be reduced to only 3.7% using a 784×800×800×10 DBN trained by 5,000 input samples. Finally, Power dissipation and accuracy tradeoffs for probabilistic computing mechanisms using resistive devices are identified.

Publication Date

5-30-2018

Publication Title

Proceedings of the ACM Great Lakes Symposium on VLSI, GLSVLSI

Number of Pages

15-20

Document Type

Article; Proceedings Paper

Personal Identifier

scopus

DOI Link

https://doi.org/10.1145/3194554.3194558

Socpus ID

85049422712 (Scopus)

Source API URL

https://api.elsevier.com/content/abstract/scopus_id/85049422712

This document is currently not available here.

Share

COinS