Design and Efficient Hardware Implementation of Spiking Neural Networks on FPGA

Please enable javascript in your browser.

Amirshahi, Alireza | 2018

367 Viewed

Type of Document: M.Sc. Thesis
Language: Farsi
Document No: 51378 (05)
University: Sharif University of Technology
Department: Electrical Engineering
Advisor(s): Hashemi, Matin
Abstract:
Spiking Neural Networks(SNN) are networks which are consisted of layers of neurons, like other typical artificial neural networks. The main difference between SNN and other neural networks is the type of data transportation among neurons which is done by spikes. Spiking neural networks and their models are considered as the nearest networks and neurons to animals’ nervous systems. In aspects of hardware implementation, the type of data transportation in SNN causes them to be ultra-low power. So, implementation of these networks on chips like FPGA and also usage of SNN in applications with high processing load have startling germination, recently. In this work, we have tried to propose some algorithms in designing and implementing some spiking neural networks for the purpose of detecting heart arrhythmia from electrocardiograms(ECG). The result indicates that not only is the design low power but also it’s accuracy in detecting arrhythmia is near the results which are obtained recently by other machine learning techniques
Keywords:
Spiking Neural Network ; Hardware Implementation ; Electrocardiogram ; Reinforcement Learning ; Field Programmable Gate Array (FPGA)

No TOC