System Design and Implementation of a Fast and Accurate Bio-Inspired Spiking Neural Network

Abstract

All rights reserved.iv DEDICATION This dissertation is dedicated to the following people:• My wife, Yanyan Pan, who has shared the life uncertainties and challenges during the completion of this dissertation, yet been always patient and supportive of my work.• My parents, Yimin Wang and Wenhua Li, who emphasized the importance of education and always encouraged me even from thousands of miles away.• My son, Lucas Wang, who has grown into a cute one year old boy in spite of his father spending so much time away from him working on this dissertation. Interictal spike (IS) is a type of transient discharge commonly found in the electroencephalography (EEG) records from epilepsy patients. The detection of IS remains an essential task for 3D source localization as well as in developing algorithms for essential in seizure prediction and guided therapy. We present in this work a new IS detection technology method using the phase encoding method with customized wavelet sensor neuron and a specially designed ASNN structure. The detection results confirm the ability of such ASNN to capture IS automatically from multichannel EEG records.