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
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390001205218492800
-
- NII論文ID
- 130006320947
-
- ISSN
- 13492543
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- Crossref
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用不可