A Current-Mode Analog Circuit for Reinforcement Learning Problems
Name
Poon_A Current-Mode Analog.pdf
Size
343.71 KB
Format
Adobe PDF
Checksum (MD5)
2911e134093c9214b079e421a6a25a63
Author(s)
Mak, Terrence S. T.
Lam, K. P.
Ng, H. S.
Rachmuth, Guy
Poon, Chi-Sang
Date Issued
June 2007
Journal
IEEE International Circuits and Systems, 2007
Publisher
Institute of Electrical and Electronics Engineers
Citation
Mak, T.S.T. et al. “A Current-Mode Analog Circuit for Reinforcement Learning Problems.” Circuits and Systems, 2007. ISCAS 2007. IEEE International Symposium on. 2007. 1301-1304. © 2007 Institute of Electrical and Electronics Engineers
Version
Final published version
Abstract
Reinforcement learning is important for machine-intelligence and neurophysiological modelling applications to provide time-critical decision making. Analog circuit implementation has been demonstrated as a powerful computational platform for power-efficient, bio-implantable and real-time applications. This paper presents a current-mode analog circuit design for solving reinforcement learning problem with simple and efficient computational network architecture. The design has been fabricated and a new procedure to validate the fabricated reinforcement learning circuit will also be presented. This work provides a preliminary study for future biomedical application using CMOS VLSI reinforcement learning model.
MIT Department
Harvard University--MIT Division of Health Sciences and Technology
Terms of Use
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Persistent DSpace Link
DOI of Published Version
http://dx.doi.org/10.1109/ISCAS.2007.378410
