Reinforcement Learning System Comprising Resistive Analog Neuromorphic Devices

Song Ju Kim, Kaori Ohkoda, Masashi Aono, Hisashi Shima, Makoto Takahashi, Yasuhisa Naitoh, Hiroyuki Akinaga

研究成果: Conference contribution

1 被引用数 (Scopus)

抄録

Reinforcement learning algorithms are widely used in many practical artificial-intelligence (AI) applications. Herein, we propose a compact hardware-based learning system comprising analogue resistive memory devices called 'resistive analogue neuromorphic devices (RAND).' We begin by showing that the resistance of a RAND linearly varies with the voltage pulses, meaning that a single RAND is sufficient to solve a reinforcement learning problem (i.e. the '2-armed bandit problem') using 'tug-of-war (TOW) dynamics.' Next, we show that 2k-armed bandit problems are also solved by hierarchically combining 2k-1 RANDs. Finally, we numerically demonstrate that the proposed methods are promising as compared with conventional methods.

本文言語English
ホスト出版物のタイトル2019 IEEE International Reliability Physics Symposium, IRPS 2019
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9781538695043
DOI
出版ステータスPublished - 2019 5 22
イベント2019 IEEE International Reliability Physics Symposium, IRPS 2019 - Monterey, United States
継続期間: 2019 3 312019 4 4

出版物シリーズ

名前IEEE International Reliability Physics Symposium Proceedings
2019-March
ISSN(印刷版)1541-7026

Conference

Conference2019 IEEE International Reliability Physics Symposium, IRPS 2019
国/地域United States
CityMonterey
Period19/3/3119/4/4

ASJC Scopus subject areas

  • 工学(全般)

フィンガープリント

「Reinforcement Learning System Comprising Resistive Analog Neuromorphic Devices」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル