English

Memristive Stochastic Computing for Deep Learning Parameter Optimization

Emerging Technologies 2021-03-18 v1 Artificial Intelligence Hardware Architecture Machine Learning

Abstract

Stochastic Computing (SC) is a computing paradigm that allows for the low-cost and low-power computation of various arithmetic operations using stochastic bit streams and digital logic. In contrast to conventional representation schemes used within the binary domain, the sequence of bit streams in the stochastic domain is inconsequential, and computation is usually non-deterministic. In this brief, we exploit the stochasticity during switching of probabilistic Conductive Bridging RAM (CBRAM) devices to efficiently generate stochastic bit streams in order to perform Deep Learning (DL) parameter optimization, reducing the size of Multiply and Accumulate (MAC) units by 5 orders of magnitude. We demonstrate that in using a 40-nm Complementary Metal Oxide Semiconductor (CMOS) process our scalable architecture occupies 1.55mm2^2 and consumes approximately 167μ\muW when optimizing parameters of a Convolutional Neural Network (CNN) while it is being trained for a character recognition task, observing no notable reduction in accuracy post-training.

Keywords

Cite

@article{arxiv.2103.06506,
  title  = {Memristive Stochastic Computing for Deep Learning Parameter Optimization},
  author = {Corey Lammie and Jason K. Eshraghian and Wei D. Lu and Mostafa Rahimi Azghadi},
  journal= {arXiv preprint arXiv:2103.06506},
  year   = {2021}
}

Comments

Accepted by IEEE Transactions on Circuits and Systems Part II: Express Briefs