Dynamic Homeostatic Regulation in Energy-Efficient Time-Locked Neuromorphic Systems

Conference Paper (2020)
Author(s)

Amir Zjajo (TU Delft - Signal Processing Systems)

DOI related publication
https://doi.org/10.1109/BIBE50027.2020.00122 Final published version
More Info
expand_more
Publication Year
2020
Language
English
Article number
9288027
Pages (from-to)
719-722
ISBN (print)
978-1-7281-9575-9
ISBN (electronic)
978-1-7281-9574-2
Event
2020 IEEE 20th International Conference on Bioinformatics and Bioengineering (BIBE) (2020-10-26 - 2020-10-28), Cincinnati, United States
Downloads counter
133

Abstract

In this paper, we present neuromorphic system with built-in temporal control that allows the implementation of transient mechanisms and homeostatic regulation. Due to the interaction between conductance delay and plasticity rules, the network is forming a set of neuronal groups with time-locked, reproducible, and precise firing patterns. Experimental results obtained in 65 nm CMOS technology illustrate the feasibility of the methodology.