Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting

• URL: http://arxiv.org/abs/2202.11946v1
• Date: Thu, 24 Feb 2022 08:02:37 GMT
• Title: Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting
• Authors: Shikuang Deng, Yuhang Li, Shanghang Zhang, Shi Gu
• Abstract summary: Brain-inspired spiking neuron networks (SNNs) have attracted widespread research interest because of their event-driven and energy-efficient characteristics. Current direct training approach with surrogate gradient results in SNNs with poor generalizability. We introduce the temporal efficient training (TET) approach to compensate for the loss of momentum in the gradient descent with SG.
• Score: 29.685909045226847
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recently, brain-inspired spiking neuron networks (SNNs) have attracted widespread research interest because of their event-driven and energy-efficient characteristics. Still, it is difficult to efficiently train deep SNNs due to the non-differentiability of its activation function, which disables the typically used gradient descent approaches for traditional artificial neural networks (ANNs). Although the adoption of surrogate gradient (SG) formally allows for the back-propagation of losses, the discrete spiking mechanism actually differentiates the loss landscape of SNNs from that of ANNs, failing the surrogate gradient methods to achieve comparable accuracy as for ANNs. In this paper, we first analyze why the current direct training approach with surrogate gradient results in SNNs with poor generalizability. Then we introduce the temporal efficient training (TET) approach to compensate for the loss of momentum in the gradient descent with SG so that the training process can converge into flatter minima with better generalizability. Meanwhile, we demonstrate that TET improves the temporal scalability of SNN and induces a temporal inheritable training for acceleration. Our method consistently outperforms the SOTA on all reported mainstream datasets, including CIFAR-10/100 and ImageNet. Remarkably on DVS-CIFAR10, we obtained 83$\%$ top-1 accuracy, over 10$\%$ improvement compared to existing state of the art. Codes are available at \url{https://github.com/Gus-Lab/temporal_efficient_training}.

Related papers

• Directly Training Temporal Spiking Neural Network with Sparse Surrogate Gradient [8.516243389583702]
  Brain-inspired Spiking Neural Networks (SNNs) have attracted much attention due to their event-based computing and energy-efficient features. We propose Masked Surrogate Gradients (MSGs) to balance the effectiveness of training and the sparseness of the gradient, thereby improving the generalization ability of SNNs.
  arXiv  Detail & Related papers  (2024-06-28T04:21:32Z)
• FTBC: Forward Temporal Bias Correction for Optimizing ANN-SNN Conversion [16.9748086865693]
  Spiking Neural Networks (SNNs) offer a promising avenue for energy-efficient computing compared with Artificial Neural Networks (ANNs) In this work, we introduce a lightweight Forward Temporal Bias (FTBC) technique, aimed at enhancing conversion accuracy without the computational overhead. We further propose an algorithm for finding the temporal bias only in the forward pass, thus eliminating the computational burden of backpropagation.
  arXiv  Detail & Related papers  (2024-03-27T09:25:20Z)
• Implicit Stochastic Gradient Descent for Training Physics-informed Neural Networks [51.92362217307946]
  Physics-informed neural networks (PINNs) have effectively been demonstrated in solving forward and inverse differential equation problems. PINNs are trapped in training failures when the target functions to be approximated exhibit high-frequency or multi-scale features. In this paper, we propose to employ implicit gradient descent (ISGD) method to train PINNs for improving the stability of training process.
  arXiv  Detail & Related papers  (2023-03-03T08:17:47Z)
• SPIDE: A Purely Spike-based Method for Training Feedback Spiking Neural Networks [56.35403810762512]
  Spiking neural networks (SNNs) with event-based computation are promising brain-inspired models for energy-efficient applications on neuromorphic hardware. We study spike-based implicit differentiation on the equilibrium state (SPIDE) that extends the recently proposed training method.
  arXiv  Detail & Related papers  (2023-02-01T04:22:59Z)
• Exact Gradient Computation for Spiking Neural Networks Through Forward Propagation [39.33537954568678]
  Spiking neural networks (SNN) have emerged as alternatives to traditional neural networks. We propose a novel training algorithm, called emphforward propagation (FP), that computes exact gradients for SNN.
  arXiv  Detail & Related papers  (2022-10-18T20:28:21Z)
• Online Training Through Time for Spiking Neural Networks [66.7744060103562]
  Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Recent progress in training methods has enabled successful deep SNNs on large-scale tasks with low latency. We propose online training through time (OTTT) for SNNs, which is derived from BPTT to enable forward-in-time learning.
  arXiv  Detail & Related papers  (2022-10-09T07:47:56Z)
• Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation [70.75043144299168]
  Spiking Neural Network (SNN) is a promising energy-efficient AI model when implemented on neuromorphic hardware. It is a challenge to efficiently train SNNs due to their non-differentiability. We propose the Differentiation on Spike Representation (DSR) method, which could achieve high performance.
  arXiv  Detail & Related papers  (2022-05-01T12:44:49Z)
• HIRE-SNN: Harnessing the Inherent Robustness of Energy-Efficient Deep Spiking Neural Networks by Training with Crafted Input Noise [13.904091056365765]
  We present an SNN training algorithm that uses crafted input noise and incurs no additional training time. Compared to standard trained direct input SNNs, our trained models yield improved classification accuracy of up to 13.7%. Our models also outperform inherently robust SNNs trained on rate-coded inputs with improved or similar classification performance on attack-generated images.
  arXiv  Detail & Related papers  (2021-10-06T16:48:48Z)
• Gradient Descent on Neural Networks Typically Occurs at the Edge of Stability [94.4070247697549]
  Full-batch gradient descent on neural network training objectives operates in a regime we call the Edge of Stability. In this regime, the maximum eigenvalue of the training loss Hessian hovers just above the numerical value $2 / text(step size)$, and the training loss behaves non-monotonically over short timescales, yet consistently decreases over long timescales.
  arXiv  Detail & Related papers  (2021-02-26T22:08:19Z)
• Progressive Tandem Learning for Pattern Recognition with Deep Spiking Neural Networks [80.15411508088522]
  Spiking neural networks (SNNs) have shown advantages over traditional artificial neural networks (ANNs) for low latency and high computational efficiency. We propose a novel ANN-to-SNN conversion and layer-wise learning framework for rapid and efficient pattern recognition.
  arXiv  Detail & Related papers  (2020-07-02T15:38:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.