Navigation auf zora.uzh.ch

Search

ZORA (Zurich Open Repository and Archive)

A compact ultra low-power pulse delay and extension circuit for neuromorphic processors

Nielsen, Carsten; Qiao, Ning; Indiveri, Giacomo (2017). A compact ultra low-power pulse delay and extension circuit for neuromorphic processors. In: Biomedical Circuits and Systems Conference (BioCAS), 2017, Turin, 19 October 2017 - 21 October 2017. IEEE, 689-692.

Abstract

Although silicon neurons communicate among each other using fast spikes, neuromorphic architectures often require long delays and pulse lengths to process temporal signals. In this paper we present a compact and power efficient pulse extension circuit that can convert short spike events into delayed pulses with configurable delay and pulse lengths that range from fractions of microseconds up to tens of milliseconds. The circuit proposed can be used to realize programmable axonal delays in neuromorphic architectures and to support the generation of synaptic dynamics with biologically plausible pulse lengths in mixed-signal analog/digital circuits. To validate the proposed scheme, we designed the pulse delay and extension circuit using a standard 0.18 μm CMOS process and performed post-layout Monte Carlo simulations. We describe the circuit and demonstrate how it can be configured to obtain biological long configurable delays and extension periods. We assess its operation via circuit simulation results and present an analysis of the Monte Carlo simulations that shows how the proposed circuit is resistant to mismatch with a standard deviation in the produced delay and pulse periods of less than 2%.

Additional indexing

Item Type:Conference or Workshop Item (Speech), not_refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Scopus Subject Areas:Physical Sciences > Biomedical Engineering
Physical Sciences > Electrical and Electronic Engineering
Physical Sciences > Instrumentation
Language:English
Event End Date:21 October 2017
Deposited On:12 Mar 2019 16:53
Last Modified:26 Jan 2022 21:12
Publisher:IEEE
Number of Pages:4
OA Status:Closed
Publisher DOI:https://doi.org/10.1109/BIOCAS.2017.8325234

Metadata Export

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

0 downloads since deposited on 12 Mar 2019
0 downloads since 12 months

Authors, Affiliations, Collaborations

Similar Publications