Publication Date

5-2021

Date of Final Oral Examination (Defense)

3-3-2021

Type of Culminating Activity

Dissertation

Degree Title

Doctor of Philosophy in Electrical and Computer Engineering

Department

Electrical and Computer Engineering

Major Advisor

John N. Chiasson, Ph.D.

Major Advisor

Vishal Saxena, Ph.D.

Advisor

Hao Chen, Ph.D.

Advisor

Hani Mehrpouyan, Ph.D.

Advisor

Saeed Reza Kheradpisheh, Ph.D.

Abstract

Spiking neural networks are biologically plausible counterparts of artificial neural networks. Artificial neural networks are usually trained with stochastic gradient descent (SGD) and spiking neural networks are trained with bioinspired spike timing dependent plasticity (STDP). Spiking networks could potentially help in reducing power usage owing to their binary activations. In this work, we use unsupervised STDP in the feature extraction layers of a neural network with instantaneous neurons to extract meaningful features. The extracted binary feature vectors are then classified using classification layers containing neurons with binary activations. Gradient descent (backpropagation) is used only on the output layer to perform training for classification. Surrogate gradients are proposed to perform backpropagation with binary gradients. The accuracies obtained for MNIST and the balanced EMNIST data set compare favorably with other approaches. The effect of the stochastic gradient descent (SGD) approximations on learning capabilities of our network are also explored. We also studied catastrophic forgetting and its effect on spiking neural networks (SNNs). For the experiments regarding catastrophic forgetting, in the classification sections of the network we use a modified synaptic intelligence that we refer to as cost per synapse metric as a regularizer to immunize the network against catastrophic forgetting in a Single-Incremental-Task scenario (SIT). In catastrophic forgetting experiments, we use MNIST and EMNIST handwritten digits datasets that were divided into five and ten incremental subtasks respectively. We also examine behavior of the spiking neural network and empirically study the effect of various hyperparameters on its learning capabilities using the software tool SPYKEFLOW that we developed. We employ MNIST, EMNIST and NMNIST data sets to produce our results.

DOI

https://doi.org/10.18122/td.1782.boisestate

Included in

Engineering Commons

Share

COinS