TechRxiv
paper_final.pdf (4.88 MB)
Download file

Self-Evolutionary Neuron Model for Fast-Response Spiking Neural Networks

Download (4.88 MB)
preprint
posted on 05.01.2022, 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.

History

Email Address of Submitting Author

anguo.zhang@hotmail.com

ORCID of Submitting Author

0000-0002-4825-7054

Submitting Author's Institution

Fuzhou University

Submitting Author's Country

China

Usage metrics

Read the peer-reviewed publication

in IEEE Transactions on Cognitive and Developmental Systems

Licence

Exports