1. An Efficient and Reconfigurable Synchronous Neuron Model
- Author
-
Hamid Soleimani and E. M. Drakakise
- Subjects
Spiking neural network ,Technology ,Electrical & Electronic Engineering ,Science & Technology ,Computer science ,020208 electrical & electronic engineering ,0906 Electrical And Electronic Engineering ,Engineering, Electrical & Electronic ,Biological neuron model ,02 engineering and technology ,Parallel computing ,Large scale simulation ,spiking neural network ,Hardware synthesis ,synchronous cellular neuron model ,Engineering ,IMPLEMENTATION ,0202 electrical engineering, electronic engineering, information engineering ,Electronic engineering ,field programable gate array (FPGA) ,Overhead (computing) ,020201 artificial intelligence & image processing ,Electrical and Electronic Engineering ,Piecewise linear model ,Electronic circuit - Abstract
This brief presents a reconfigurable and efficient 2-D neuron model capable of extending to higher dimensions. The model is applied to the Izhikevich and FitzHugh-Nagumo neuron models as 2-D case studies and to the Hindmarsh-Rose model as a 3-D case study. Hardware synthesis and physical implementations show that the resulting circuits can reproduce neural dynamics with acceptable precision and considerably low hardware overhead compared to previously published piecewise linear models.
- Published
- 2018
- Full Text
- View/download PDF