Download PDFOpen PDF in browser

Exploiting Correlation in Stochastic Computing Based Deep Neural Networks

EasyChair Preprint no. 6541

6 pagesDate: September 4, 2021

Abstract

A new trans-disciplinary knowledge area, Edge Artificial Intelligence or Edge Intelligence, is beginning to receive a tremendous amount of interest. Unfortunately, the incorporation of AI characteristics to edge computing devices presents the drawbacks of being power and area hungry for typical machine learning techniques such as Convolutional Neural Networks (CNN). In this work, we propose a new power-and-area-efficient architecture for implementing Artificial Neural Networks (ANNs) in hardware, based on the exploitation of correlation phenomenon in Stochastic Computing (SC) systems. The architecture purposed can solve the difficult implementation challenges that SC presents for CNN applications, such as the high resources used in binary-to-stochastic conversion, the inaccuracy produced by undesired correlation between signals, and the stochastic maximum function implementation.
Compared with traditional binary logic implementations, experimental results showed an improvement of 19.6x and 6.3x in terms of speed performance and energy efficiency, for the FPGA implementation. For the first time, a fully-parallel CNN as LENET-5 is embedded and tested in a single FPGA, showing the benefits of using stochastic computing for embedded applications, in contrast to traditional binary logic implementations.

Keyphrases: Convolutional Neural Networks, correlation, Edge Computing, FPGA, stochastic computing

BibTeX entry
BibTeX does not have the right entry for preprints. This is a hack for producing the correct reference:
@Booklet{EasyChair:6541,
  author = {Christiam Camilo Franco Frasser and Pablo Linares and Alejandro Morán and Joan Font-Rosselló and Vincens Canals and Miquel Roca and Teresa Serrano Gotarredona and Josep Lluis Rosselló},
  title = {Exploiting Correlation in Stochastic Computing Based Deep Neural Networks},
  howpublished = {EasyChair Preprint no. 6541},

  year = {EasyChair, 2021}}
Download PDFOpen PDF in browser