eWB: Event-Based Weight Binarization Algorithm for Spiking Neural Networksopen access
- Authors
- Kim, Dohun; Kim, Guhyun; Hwang, Cheol Seong; Jeong, Doo Seok
- Issue Date
- Mar-2021
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Neurons; Synapses; Classification algorithms; Approximation algorithms; Linear programming; Training; System-on-chip; Event-based weight binarization; event-driven learning algorithm; Lagrange multiplier method; spiking neural networks
- Citation
- IEEE ACCESS, v.9, pp.38097 - 38106
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE ACCESS
- Volume
- 9
- Start Page
- 38097
- End Page
- 38106
- URI
- https://scholarworks.bwise.kr/hanyang/handle/2021.sw.hanyang/1352
- DOI
- 10.1109/ACCESS.2021.3062405
- ISSN
- 2169-3536
- Abstract
- Learning binary weights to minimize the difference between target and actual outputs can be considered as a parameter optimization task within the given constraints, and thus, it belongs to the application domain of the Lagrange multiplier method (LMM). Based on the LMM, we propose a novel event-based weight binarization (eWB) algorithm for spiking neural networks (SNNs) with binary synaptic weights (-1, 1). The algorithm features (i) event-based asymptotic weight binarization using local data only, (ii) full compatibility with event-based end-to-end learning algorithms (e.g., event-driven random backpropagation (eRBP) algorithm), and (iii) the capability to address various constraints (including the binary weight constraint). As a proof of concept, we combine eWB with eRBP (eWB-eRBP) to obtain a single algorithm for learning binary weights to generate correct classifications. Fully connected SNNs were trained using eWB-eRBP and achieved an accuracy of 95.35% on MNIST. To the best of our knowledge, this is the first report on completely binary SNNs trained using an event-based learning algorithm. Given that eRBP with full-precision (32-bit) weights exhibited 97.20% accuracy, the binarization comes at the cost of an accuracy reduction of approximately 1.85%. The python code is available online: https://github.com/galactico7/eWB.
- Files in This Item
-
- Appears in
Collections - 서울 공과대학 > 서울 신소재공학부 > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.