Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratch

• URL: http://arxiv.org/abs/2010.01729v5
• Date: Wed, 10 Nov 2021 21:23:44 GMT
• Title: Revisiting Batch Normalization for Training Low-latency Deep Spiking Neural Networks from Scratch
• Authors: Youngeun Kim, Priyadarshini Panda
• Abstract summary: Spiking Neural Networks (SNNs) have emerged as an alternative to deep learning. High-accuracy and low-latency SNNs from scratch suffer from non-differentiable nature of a spiking neuron. We propose a temporal Batch Normalization Through Time (BNTT) technique for training temporal SNNs.
• Score: 5.511606249429581
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Spiking Neural Networks (SNNs) have recently emerged as an alternative to deep learning owing to sparse, asynchronous and binary event (or spike) driven processing, that can yield huge energy efficiency benefits on neuromorphic hardware. However, training high-accuracy and low-latency SNNs from scratch suffers from non-differentiable nature of a spiking neuron. To address this training issue in SNNs, we revisit batch normalization and propose a temporal Batch Normalization Through Time (BNTT) technique. Most prior SNN works till now have disregarded batch normalization deeming it ineffective for training temporal SNNs. Different from previous works, our proposed BNTT decouples the parameters in a BNTT layer along the time axis to capture the temporal dynamics of spikes. The temporally evolving learnable parameters in BNTT allow a neuron to control its spike rate through different time-steps, enabling low-latency and low-energy training from scratch. We conduct experiments on CIFAR-10, CIFAR-100, Tiny-ImageNet and event-driven DVS-CIFAR10 datasets. BNTT allows us to train deep SNN architectures from scratch, for the first time, on complex datasets with just few 25-30 time-steps. We also propose an early exit algorithm using the distribution of parameters in BNTT to reduce the latency at inference, that further improves the energy-efficiency.

Related papers

• Towards Low-latency Event-based Visual Recognition with Hybrid Step-wise Distillation Spiking Neural Networks [50.32980443749865]
  Spiking neural networks (SNNs) have garnered significant attention for their low power consumption and high biologicalability. Current SNNs struggle to balance accuracy and latency in neuromorphic datasets. We propose Step-wise Distillation (HSD) method, tailored for neuromorphic datasets.
  arXiv  Detail & Related papers  (2024-09-19T06:52:34Z)
• TT-SNN: Tensor Train Decomposition for Efficient Spiking Neural Network Training [27.565726483503838]
  We introduce Train Decomposition for Spiking Neural Networks (TT-SNN) TT-SNN reduces model size through trainable weight decomposition, resulting in reduced storage, FLOPs, and latency. We also propose a parallel computation as an alternative to the typical sequential tensor computation.
  arXiv  Detail & Related papers  (2024-01-15T23:08:19Z)
• LC-TTFS: Towards Lossless Network Conversion for Spiking Neural Networks with TTFS Coding [55.64533786293656]
  We show that our algorithm can achieve a near-perfect mapping between the activation values of an ANN and the spike times of an SNN on a number of challenging AI tasks. The study paves the way for deploying ultra-low-power TTFS-based SNNs on power-constrained edge computing platforms.
  arXiv  Detail & Related papers  (2023-10-23T14:26:16Z)
• Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks [70.75043144299168]
  Spiking Neural Networks (SNNs) are promising energy-efficient models for neuromorphic computing. We propose the Spatial Learning Through Time (SLTT) method that can achieve high performance while greatly improving training efficiency. Our method achieves state-of-the-art accuracy on ImageNet, while the memory cost and training time are reduced by more than 70% and 50%, respectively, compared with BPTT.
  arXiv  Detail & Related papers  (2023-02-28T05:01:01Z)
• 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)
• Training Energy-Efficient Deep Spiking Neural Networks with Time-to-First-Spike Coding [29.131030799324844]
  Spiking neural networks (SNNs) mimic the operations in the human brain. Deep neural networks (DNNs) have become a serious problem in deep learning. This paper presents training methods for energy-efficient deep SNNs with TTFS coding.
  arXiv  Detail & Related papers  (2021-06-04T16:02:27Z)
• Deep Time Delay Neural Network for Speech Enhancement with Full Data Learning [60.20150317299749]
  This paper proposes a deep time delay neural network (TDNN) for speech enhancement with full data learning. To make full use of the training data, we propose a full data learning method for speech enhancement.
  arXiv  Detail & Related papers  (2020-11-11T06:32:37Z)
• Going Deeper With Directly-Trained Larger Spiking Neural Networks [20.40894876501739]
  Spiking neural networks (SNNs) are promising in coding for bio-usible information and event-driven signal processing. However, the unique working mode of SNNs makes them more difficult to train than traditional networks. We propose a CIF-dependent batch normalization (tpladBN) method based on the emerging-temporal backproation threshold.
  arXiv  Detail & Related papers  (2020-10-29T07:15:52Z)
• Enabling Deep Spiking Neural Networks with Hybrid Conversion and Spike Timing Dependent Backpropagation [10.972663738092063]
  Spiking Neural Networks (SNNs) operate with asynchronous discrete events (or spikes) We present a computationally-efficient training technique for deep SNNs. We achieve top-1 accuracy of 65.19% for ImageNet dataset on SNN with 250 time steps, which is 10X faster compared to converted SNNs with similar accuracy.
  arXiv  Detail & Related papers  (2020-05-04T19:30:43Z)

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.