๐ฎ
๐ฎ
The Ethereal
Direct Training Needs Regularisation: Anytime Optimal Inference Spiking Neural Network
April 15, 2024 ยท Entered Twilight ยท ๐ arXiv.org
Repo contents: LICENSE, README.md, docs
Authors
Dengyu Wu, Yi Qi, Kaiwen Cai, Gaojie Jin, Xinping Yi, Xiaowei Huang
arXiv ID
2405.00699
Category
cs.NE: Neural & Evolutionary
Cross-listed
cs.AI,
cs.LG
Citations
6
Venue
arXiv.org
Repository
https://github.com/Dengyu-Wu/AOI-SNN-Regularisation
โญ 6
Last Checked
3 months ago
Abstract
Spiking Neural Network (SNN) is acknowledged as the next generation of Artificial Neural Network (ANN) and hold great promise in effectively processing spatial-temporal information. However, the choice of timestep becomes crucial as it significantly impacts the accuracy of the neural network training. Specifically, a smaller timestep indicates better performance in efficient computing, resulting in reduced latency and operations. While, using a small timestep may lead to low accuracy due to insufficient information presentation with few spikes. This observation motivates us to develop an SNN that is more reliable for adaptive timestep by introducing a novel regularisation technique, namely Spatial-Temporal Regulariser (STR). Our approach regulates the ratio between the strength of spikes and membrane potential at each timestep. This effectively balances spatial and temporal performance during training, ultimately resulting in an Anytime Optimal Inference (AOI) SNN. Through extensive experiments on frame-based and event-based datasets, our method, in combination with cutoff based on softmax output, achieves state-of-the-art performance in terms of both latency and accuracy. Notably, with STR and cutoff, SNN achieves 2.14 to 2.89 faster in inference compared to the pre-configured timestep with near-zero accuracy drop of 0.50% to 0.64% over the event-based datasets. Code available: https://github.com/Dengyu-Wu/AOI-SNN-Regularisation
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
๐ Similar Papers
In the same crypt โ Neural & Evolutionary
R.I.P.
๐ป
Ghosted
Deep Learning using Rectified Linear Units (ReLU)
R.I.P.
๐ป
Ghosted
Generative Adversarial Text to Image Synthesis
R.I.P.
๐ป
Ghosted
Regularized Evolution for Image Classifier Architecture Search
R.I.P.
๐ป
Ghosted
Temporal Ensembling for Semi-Supervised Learning
๐
๐
Old Age