Bifurcation Spiking Neural Network

Abstract

Spiking neural networks (SNNs) has attracted much attention due to its great potential of modeling time-dependent signals. The firing rate of spiking neurons is decided by control rate which is fixed manually in advance, and thus, whether the firing rate is adequate for modeling actual time series relies on fortune. Though it is demanded to have an adaptive control rate, it is a non-trivial task because the control rate and the connection weights learned during the training process are usually entangled. In this paper, we show that the firing rate is related to the eigenvalue of the spike generation function. Inspired by this insight, by enabling the spike generation function to have adaptable eigenvalues rather than parametric control rates, we develop the Bifurcation Spiking Neural Network (BSNN), which has an adaptive firing rate and is insensitive to the setting of control rates. Experiments validate the effectiveness of BSNN on a broad range of tasks, showing that BSNN achieves superior performance to existing SNNs and is robust to the setting of control rates.

18 pages

References in corpus (9)

• Deep Learning in Neural Networks: An Overview
• Multi-Scale Convolutional Neural Networks for Time Series Classification
• SLAYER: Spike Layer Error Reassignment in Time
• EMNIST: an extension of MNIST to handwritten letters
• Spiking Deep Networks with LIF Neurons
• Deep Spiking Networks
• Hybrid Macro/Micro Level Backpropagation for Training Deep Spiking Neural Networks
• Spike-Train Level Backpropagation for Training Deep Recurrent Spiking Neural Networks
• Flexible Transmitter Network