*********************************
There is now a CONTENT FREEZE for Mercury while we switch to a new platform. It began on Friday, March 10 at 6pm and will end on Wednesday, March 15 at noon. No new content can be created during this time, but all material in the system as of the beginning of the freeze will be migrated to the new platform, including users and groups. Functionally the new site is identical to the old one. webteam@gatech.edu
*********************************
Title: Design and Optimization of Heterogeneous Feedforward Spiking Neural Network for Spatiotemporal Data Processing
Committee:
Dr. Saibal Mukhopadhyay, ECE, Chair, Advisor
Dr. Arijit Raychowdhury, ECE
Dr. Christopher Rozell, ECE
Dr. Tushar Krishna, ECE
Dr. Hyesoon Kim, CoC
Abstract: The biologically inspired model of spiking neural network (SNN) is a type of network that is capable of processing computer vision data, and has the potential to achieve higher energy-efficiency than DNN due to its event-driven operations. SNN also has the capability to learn with biologically inspired algorithm that does not require training labels. While good performance has been shown for datasets with spatial-correlation, such as those in image classification tasks, the accuracy of SNN is still below that of DNN when the dataset has a higher level of complexity. This includes spatiotemporal tasks such as video classification and gesture recognition. In this thesis, a design methodology is proposed for feedforward SNN that can be trained with either biologically inspired unsupervised learning algorithm or supervised statistical training algorithm, to achieve spatiotemporal data processing. The proposed model shows performance that is parallel to or better than DNN when the amount of labeled training data is limited. Theoretical analysis for the feedforward SNN is developed to help optimize network performance. It is demonstrated with experimental results that the proposed optimization process can achieve networks with improved performance while using less trainable parameters than SNN baselines. Furthermore, for event-based spatiotemporal data such as event-camera data, it is demonstrated that the efficiency of the proposed SNN model can be further improved with a fully event-driven processing method.
