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

Brain Sciences

Ziyi Huan¹  Yunlin Lei¹  Xu Yang¹  Mengxing Wang¹  Miao Wang¹  Xialv Lin¹  Jian Cai¹ 

[1] School of Computer Science and Technology, Beijing Institute of Technology, Beijing 100081, China;

关键词: small-sample learning;    spiking neural network;    structural learning;    adaptive structure;   

DOI  :  10.3390/brainsci12020139

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown