paper_final.pdf (4.88 MB)
Self-Evolutionary Neuron Model for Fast-Response Spiking Neural Networks
preprintposted on 2022-01-05, 19:39 authored by Anguo ZhangAnguo Zhang, Ying Han, Jing Hu, Yuzhen Niu, Yueming Gao, ZHIZHANG CHENZHIZHANG CHEN, Kai Zhao
We propose two simple and effective spiking neuron models to improve the response time of the conventional spiking neural network. The proposed neuron models adaptively tune the presynaptic input current depending on the input received from its presynapses and subsequent neuron firing events. We analyze and derive the firing activity homeostatic convergence of the proposed models. We experimentally verify and compare the models on MNIST handwritten digits and FashionMNIST classification tasks. We show that the proposed neuron models significantly increase the response speed to the input signal.
Email Address of Submitting Authoranguo.firstname.lastname@example.org
ORCID of Submitting Author0000-0002-4825-7054
Submitting Author's InstitutionFuzhou University
Submitting Author's Country