Header

UZH-Logo

Maintenance Infos

Error-triggered Three-Factor Learning Dynamics for Crossbar Arrays


Payvand, Melika; Fouda, Mohammed E; Kurdahi, Fadi; Eltawil, Ahmed; Neftci, Emre O (2020). Error-triggered Three-Factor Learning Dynamics for Crossbar Arrays. In: 2020 2nd IEEE International Conference on Artificial Intelligence Circuits and Systems (AICAS), Genova, Italy, 31 August 2020 - 2 September 2020.

Abstract

Recent breakthroughs suggest that local, approximate gradient descent learning is compatible with Spiking Neural Networks (SNNs). Although SNNs can be scalably implemented using neuromorphic VLSI, an architecture, that can learn in situ as accurately as conventional processors, is still missing. Here, we propose a subthreshold circuit architecture designed through insights obtained from machine learning and computational neuroscience that could achieve such accuracy. Using a surrogate gradient learning framework, we derive local, error-triggered learning dynamics compatible with crossbar arrays and the temporal dynamics of SNNs. The derivation reveals that circuits used for inference and training dynamics can be shared, which simplifies the circuit and suppresses the effects of fabrication mismatch. We present SPICE simulations on XFAB 180nm process, as well as large-scale simulations of the spiking neural networks on event-based benchmarks, including a gesture recognition task. Our results show that the number of updates can be reduced hundred-fold compared to the standard rule while achieving performances that are on par with the state-of-the-art.

Abstract

Recent breakthroughs suggest that local, approximate gradient descent learning is compatible with Spiking Neural Networks (SNNs). Although SNNs can be scalably implemented using neuromorphic VLSI, an architecture, that can learn in situ as accurately as conventional processors, is still missing. Here, we propose a subthreshold circuit architecture designed through insights obtained from machine learning and computational neuroscience that could achieve such accuracy. Using a surrogate gradient learning framework, we derive local, error-triggered learning dynamics compatible with crossbar arrays and the temporal dynamics of SNNs. The derivation reveals that circuits used for inference and training dynamics can be shared, which simplifies the circuit and suppresses the effects of fabrication mismatch. We present SPICE simulations on XFAB 180nm process, as well as large-scale simulations of the spiking neural networks on event-based benchmarks, including a gesture recognition task. Our results show that the number of updates can be reduced hundred-fold compared to the standard rule while achieving performances that are on par with the state-of-the-art.

Statistics

Citations

Dimensions.ai Metrics

Altmetrics

Downloads

3 downloads since deposited on 16 Feb 2021
3 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Neuroinformatics
Dewey Decimal Classification:570 Life sciences; biology
Scopus Subject Areas:Physical Sciences > Artificial Intelligence
Physical Sciences > Computer Science Applications
Physical Sciences > Hardware and Architecture
Physical Sciences > Electrical and Electronic Engineering
Language:English
Event End Date:2 September 2020
Deposited On:16 Feb 2021 08:20
Last Modified:17 Feb 2021 21:02
Publisher:IEEE
ISBN:9781728149226
OA Status:Green
Publisher DOI:https://doi.org/10.1109/aicas48895.2020.9073998

Download

Green Open Access

Download PDF  'Error-triggered Three-Factor Learning Dynamics for Crossbar Arrays'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 488kB
View at publisher