Affiliation:
1. University of Kansas
2. Air Force Research Laboratory
3. Google Inc.
4. University of Kansa
Abstract
This article presents our research towards developing novel and fundamental methodologies for data representation using spike-timing-dependent encoding. Time encoding efficiently maps a signal's amplitude information into a spike time sequence that represents the input data and offers perfect recovery for band-limited stimuli. In this article, we pattern the neural activities across multiple timescales and encode the sensory information using time-dependent temporal scales. The spike encoding methodologies for autonomous classification of time-series signatures are explored using near-chaotic reservoir computing. The proposed spiking neuron is compact, low power, and robust. A hardware implementation of these results is expected to produce an agile hardware implementation of time encoding as a signal conditioner for dynamical neural processor designs.
Publisher
Association for Computing Machinery (ACM)
Subject
Electrical and Electronic Engineering,Hardware and Architecture,Software
Reference77 articles.
1. Lapicque’s introduction of the integrate-and-fire model neuron (1907)
2. P. E. Allen and D. R. Holberg. 2002. CMOS Analog Circuit Design. Oxford University Press. P. E. Allen and D. R. Holberg. 2002. CMOS Analog Circuit Design. Oxford University Press.
3. Silicon-neuron design: A dynamical systems approach;Arthur J. V.;IEEE Trans. Circ. Syst.,2011
4. A subthreshold mos neuron circuit based on the volterra system
Cited by
29 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献