期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
卷 69, 期 3, 页码 1832-1836出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSII.2021.3124666
关键词
Neurons; Bifurcation; Adaptation models; Mathematical models; Trajectory; Numerical models; Numerical stability; Activation function; adaptive synaptic neuron; circuit implementation; hardware experiment; neuron dynamics
资金
- National Natural Science Foundation of China [61801054, 51777016]
- Natural Science Foundation of Jiangsu Province, China [BK20160282]
- Postgraduate Research and Practice Innovation Program of Jiangsu Province, China [KYCX21_2824]
The complex activation functions in the adaptive synaptic neuron model result in complicated hardware implementations, which hinder its applications. This paper presents a piecewise-linear activation function with simplified circuit implementation, which proves its superiority in emulating neuron dynamics through hardware experiments.
Adaptive synaptic neuron model involves complex activation functions. These nonlinearities lead to complicated hardware implementations, which greatly hinder neuron-based applications. To effectively solve this issue, a piecewise-linear (PWL) activation function with simplified circuit implementation is presented for the adaptive synaptic neuron model in this brief. With this neuron model, the stability evolution mechanism of the equilibrium state is analyzed and the parameter- and initial condition-related neuron dynamics are numerically explored. Afterwards, an analog circuit is designed and manually made using commercially available components. The phase trajectories captured by the hardware experiments verify the feasibility of the PWL activation function. Thus, such a PWL simplification shows superiority in emulating neuron dynamics.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据