Evaluation of the Effect of the Dynamic Behavior and Topology Co-Learning of Neurons and Synapses on the Small-Sample Learning Ability of Spiking Neural Network

Abstract

Small sample learning ability is one of the most significant characteristics of the human brain. However, its mechanism is yet to be fully unveiled. In recent years, brain-inspired artificial intelligence has become a very hot research domain. Researchers explored brain-inspired technologies or architectures to construct neural networks that could achieve human-alike intelligence. In this work, we presented our effort at evaluation of the effect of dynamic behavior and topology co-learning of neurons and synapses on the small sample learning ability of spiking neural network. Results show that the dynamic behavior and topology co-learning mechanism of neurons and synapses presented in our work could significantly reduce the number of required samples, while maintaining a reasonable performance on the MNIST data-set, resulting in a very lightweight neural network structure.

Anti-Disturbance of Scale-Free Spiking Neural Network against Impulse Noise

“…Drawing from the advantages of the bio-brain to investigate the robustness function of a spiking neural network (SNN) is conducive to the advancement of brain-like intelligence. An SNN with neuron dynamics and synaptic weight dynamics has a strong ability to process nonlinear spatiotemporal information, which means the SNN is widely applied in the field of computational neuroscience [4][5][6]. The three basic elements of SNN construction are the neuron model, the synaptic plasticity model, and the network topology.…”