期刊
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
卷 69, 期 10, 页码 4138-4142出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCSII.2022.3187623
关键词
Neurons; Mathematical models; Biological system modeling; Computational modeling; Hardware; Calcium; Integrated circuit modeling; Spiking neurons; morris-lecar neuron; neuromorphic hardware; FPGA
A highly accurate digital implementation of the Morris-Lecar neuron model is proposed for hardware acceleration in neuroscience simulation. The implementation utilizes the COordinate Rotation DIgital Computer (CORDIC) algorithm to create a fixed-point implementation that is both highly accurate and requires low digital hardware resources. Compared to the current state-of-the-art, this design achieves higher accuracy, requires fewer hardware resources, and operates at a higher maximum clock frequency. The design is validated on FPGA with a normalized RMSE of 0.2039 at a maximum clock frequency of 378.07MHz.
A highly accurate digital implementation of the Morris-Lecar neuron model is presented with the intended application of hardware acceleration for neuroscience simulation. The novel implementation employs the COordinate Rotation DIgital Computer (CORDIC) algorithm to create a fixed-point implementation that is not only very accurate but requires low digital hardware resources. The accuracy exceeds that of the current state-of-the-art, requires fewer hardware resources to implement, and operates at a higher maximum clock frequency. The design is validated on FPGA and a normalized RMSE of 0.2039 is achieved at a maximum clock frequency of 378.07MHz.
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