eWB: Event-Based Weight Binarization Algorithm for Spiking Neural Networks

IEEE Access

Dohun Kim¹  Cheol Seong Hwang¹  Guhyun Kim²  Doo Seok Jeong² 

[1] Department of Material Science and Engineering, Seoul National University, Seoul, Republic of Korea;Division of Materials Science and Engineering, Hanyang University, Seoul, Republic of Korea;

关键词: Event-based weight binarization;    event-driven learning algorithm;    Lagrange multiplier method;    spiking neural networks;   

DOI  :  10.1109/ACCESS.2021.3062405

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown