A current-mode analog circuit for reinforcement learning problems
Refereed conference paper presented and published in conference proceedings


Times Cited
Web of Science1WOS source URL (as at 31/07/2020) Click here for the latest count
Altmetrics Information
.

Other information
AbstractReinforcement 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. In this paper, we present a current-mode analog circuit design for solving reinforcement learning problem with a simple and efficient computational network architecture. Our 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.
All Author(s) ListMak TST, Lam KR, Ng HS, Rachmuth G, Poon CS
Name of ConferenceIEEE International Symposium on Circuits and Systems
Start Date of Conference27/05/2007
End Date of Conference30/05/2007
Place of ConferenceNew Orleans
Country/Region of ConferenceUnited States of America
Year2007
Month1
Day1
PublisherIEEE
Pages1301 - 1304
ISBN978-1-4244-0920-4
ISSN0271-4302
LanguagesEnglish-United Kingdom
Web of Science Subject CategoriesComputer Science; Computer Science, Artificial Intelligence; Computer Science, Software Engineering; Engineering; Engineering, Biomedical; Engineering, Electrical & Electronic; Imaging Science & Photographic Technology; Mathematical & Computational Biology; Nanoscience & Nanotechnology; Science & Technology - Other Topics; Telecommunications

Last updated on 2020-31-07 at 23:31