Online Pseudo-Zeroth-Order Training of Neuromorphic Spiking Neural Networks

• URL: http://arxiv.org/abs/2407.12516v1
• Date: Wed, 17 Jul 2024 12:09:00 GMT
• Title: Online Pseudo-Zeroth-Order Training of Neuromorphic Spiking Neural Networks
• Authors: Mingqing Xiao, Qingyan Meng, Zongpeng Zhang, Di He, Zhouchen Lin,
• Abstract summary: Brain-inspired neuromorphic computing with spiking neural networks (SNNs) is a promising energy-efficient computational approach. Most recent methods leverage spatial and temporal backpropagation (BP), not adhering to neuromorphic properties. We propose a novel method, online pseudo-zeroth-order (OPZO) training.
• Score: 69.2642802272367
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Brain-inspired neuromorphic computing with spiking neural networks (SNNs) is a promising energy-efficient computational approach. However, successfully training SNNs in a more biologically plausible and neuromorphic-hardware-friendly way is still challenging. Most recent methods leverage spatial and temporal backpropagation (BP), not adhering to neuromorphic properties. Despite the efforts of some online training methods, tackling spatial credit assignments by alternatives with comparable performance as spatial BP remains a significant problem. In this work, we propose a novel method, online pseudo-zeroth-order (OPZO) training. Our method only requires a single forward propagation with noise injection and direct top-down signals for spatial credit assignment, avoiding spatial BP's problem of symmetric weights and separate phases for layer-by-layer forward-backward propagation. OPZO solves the large variance problem of zeroth-order methods by the pseudo-zeroth-order formulation and momentum feedback connections, while having more guarantees than random feedback. Combining online training, OPZO can pave paths to on-chip SNN training. Experiments on neuromorphic and static datasets with fully connected and convolutional networks demonstrate the effectiveness of OPZO with similar performance compared with spatial BP, as well as estimated low training costs.

Related papers

• Asymmetrical estimator for training encapsulated deep photonic neural networks [10.709758849326061]
  asymmetrical training (AT) is a BP-based training method that can perform training on an encapsulated deep network. AT offers significantly improved time and energy efficiency compared to existing BP-PNN methods. We demonstrate AT's error-tolerant and calibration-free training for encapsulated integrated photonic deep networks.
  arXiv  Detail & Related papers  (2024-05-28T17:27:20Z)
• Biologically-Plausible Topology Improved Spiking Actor Network for Efficient Deep Reinforcement Learning [15.143466733327566]
  Recent advances in neuroscience have unveiled that the human brain achieves efficient reward-based learning. The success of Deep Reinforcement Learning (DRL) is largely attributed to utilizing Artificial Neural Networks (ANNs) as function approximators. We propose a novel alternative for function approximator, the Biologically-Plausible Topology improved Spiking Actor Network (BPT-SAN)
  arXiv  Detail & Related papers  (2024-03-29T13:25:19Z)
• Forward Direct Feedback Alignment for Online Gradient Estimates of Spiking Neural Networks [0.0]
  Spiking neural networks can be simulated energy efficiently on neuromorphic hardware platforms. We propose a novel neuromorphic algorithm, the textitSpiking Forward Direct Feedback Alignment (SFDFA) algorithm.
  arXiv  Detail & Related papers  (2024-02-06T09:07:12Z)
• Fully Spiking Actor Network with Intra-layer Connections for Reinforcement Learning [51.386945803485084]
  We focus on the task where the agent needs to learn multi-dimensional deterministic policies to control. Most existing spike-based RL methods take the firing rate as the output of SNNs, and convert it to represent continuous action space (i.e., the deterministic policy) through a fully-connected layer. To develop a fully spiking actor network without any floating-point matrix operations, we draw inspiration from the non-spiking interneurons found in insects.
  arXiv  Detail & Related papers  (2024-01-09T07:31:34Z)
• 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)
• Multi-Level Firing with Spiking DS-ResNet: Enabling Better and Deeper Directly-Trained Spiking Neural Networks [19.490903216456758]
  Spiking neural networks (SNNs) are neural networks with asynchronous discrete and sparse characteristics. We propose a multi-level firing (MLF) method based on the existing spiking-suppressed residual network (spiking DS-ResNet)
  arXiv  Detail & Related papers  (2022-10-12T16:39:46Z)
• 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 Feedback Spiking Neural Networks by Implicit Differentiation on the Equilibrium State [66.2457134675891]
  Spiking neural networks (SNNs) are brain-inspired models that enable energy-efficient implementation on neuromorphic hardware. Most existing methods imitate the backpropagation framework and feedforward architectures for artificial neural networks. We propose a novel training method that does not rely on the exact reverse of the forward computation.
  arXiv  Detail & Related papers  (2021-09-29T07:46:54Z)
• Selfish Sparse RNN Training [13.165729746380816]
  We propose an approach to train sparse RNNs with a fixed parameter count in one single run, without compromising performance. We achieve state-of-the-art sparse training results with various datasets on Penn TreeBank and Wikitext-2.
  arXiv  Detail & Related papers  (2021-01-22T10:45:40Z)

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.