Learning Local Representation by Gradient-Isolated Memorizing of Spiking Neural Network
Lists
Only you see this
Abstract
Spiking neural networks (SNNs) show promise in implementing low-power AI hardware due to their event-driven sparsity and leaky integrate-and-fire (LIF) neurons with binary spikes, rather than traditional activation functions with analog output. However, SNNs have a low capacity to process the local input due to their spike encoding paradigm. To address these problems, we propose a novel SNN architecture with a gradient-isolated memorizing mechanism, horizontal LIF, and vertical LIF neurons to learn local representation. Moreover, to take full advantage of local representations and global representations, we design a concurrent SNN architecture within the local-global joint representation. For proof-of-concept, we evaluate our proposal on MNIST, Fashion MNIST, and CIFAR-10 datasets, which achieve 98.68% and 90.37%, and 87.19% accuracy with 5 time steps, respectively, while maintaining low computational complexity.
BibTeX
@inproceedings{wu2022learning,
author = {Man Wu and Zheng Chen and Yunpeng Yao},
title = {{Learning Local Representation by Gradient-Isolated Memorizing of Spiking Neural Network}},
booktitle = {HPCC/DSS/SmartCity/DependSys},
year = {2022},
url = {https://openreview.net/forum?id=l7yuBI3o7M},
}Loading related content...