This paper introduces seven brain-inspired rules that are deeply rooted in the understanding of the brain to improve multi-layer spiking neural networks (SNNs). The dynamics of neurons, synapses, and plasticity models are considered to be major characteristics of information processing in brain neural networks. Hence, incorporating these models and rules to traditional SNNs is expected to improve their efficiency. The proposed SNN model can mainly be divided into three parts: the spike generation layer, the hidden layers, and the output layer. In the spike generation layer, non-temporary signals such as static images are converted into spikes by both local and global feature-converting methods. In the hidden layers, the rules of dynamic neurons, synapses, the proportion of different kinds of neurons, and various spike timing dependent plasticity (STDP) models are incorporated. In the output layer, the function of classification for excitatory neurons and winner take all (WTA) for inhibitory neurons are realized. MNIST dataset is used to validate the classification accuracy of the proposed neural network model. Experimental results show that higher accuracy will be achieved when more brain-inspired rules (with careful selection) are integrated into the learning procedure.
This work was supported by Strategic Priority Research Program of Chinese Academy of Sciences (Grant No. XDB02060007), and Beijing Municipal Commission of Science and Technology (Grant Nos. Z151100000915070, Z161100000216124).
(Color online) The architecture of multi-layer SNN.
(Color online) The global feature converting method.
(Color online) The local feature converting method.
The accuracies of different proportions and types of inhibitory neurons. Initial synaptic connection is 50%. All the results are based on the integrated rules of
The convergence time of different proportions and types of inhibitory neurons.
The accuracy and convergence time of classification results based on different features detection method (the convergence time is normalized).
The improving accuracies based on gradually incorporating more brain-inspired learning rules.
Copyright 2020 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有