A novel memristor-based restricted Boltzmann machine for contrastive divergence

  • Chen Yan
    College of Electrical and Information Engineering, Hunan University
  • You Zhiqiang
    College of Computer Science and Electronic Engineering, Hunan University
  • Zhang Yingjie
    College of Computer Science and Electronic Engineering, Hunan University
  • Kuang Jishun
    College of Computer Science and Electronic Engineering, Hunan University
  • Zhang Jing
    College of Electrical and Information Engineering, Hunan University

抄録

<p>In this letter, we present a novel memristor-based restricted Boltzmann machine (RBM) system for training the brain-scale neural network applications. The proposed system delicately integrates the storage component of neuron outputs and the component of multiply-accumulate (MAC) in memory, allowed operating both of them in the same stage cycle and less memory access for the contrastive divergence (CD) training. Experimental results show that the proposed system delivers significantly 2770x speedup and less than 1% accuracy loss against the x86-CPU platform on RBM applications. On average, it achieves 2.3x faster performance and 2.1x better energy efficiency over recent state-of-the-art RBM training systems.</p>

収録刊行物

  • IEICE Electronics Express

    IEICE Electronics Express 15 (2), 20171062-20171062, 2018

    一般社団法人 電子情報通信学会

被引用文献 (5)*注記

もっと見る

参考文献 (8)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ