Date of Graduation
5-2026
Document Type
Thesis
Degree Name
Bachelor of Science in Electrical Engineering
Degree Level
Undergraduate
Department
Electrical Engineering
Advisor/Mentor
Dr. Jeff Dix
Abstract
A small-scale analog schematic of a spiking neural network (SNN) is designed and demonstrated through the analog design environment (ADE) within Cadence Virtuoso. An SNN is a type of neuromorphic system that utilizes components mimicking the function of the neurons and synapses found in biological neural networks. The SNN designed in this project is composed of four layers: one input layer, two hidden layers, and one output layer. The inclusion of more than one hidden layer classifies the network as “deep” and increases the network’s efficiency at handling data with increased complexity. The SNN categorizes inputs by producing a set of differently weighted sums of the inputs, then producing weighted sums of the weighted sums that cleared a threshold, and continuing until the output layer produces its set of sums and has a chance of creating output spikes. The capability of the circuit to categorize inputs is tested by having it categorize clustered datapoints on a coordinate plane.
Keywords
electronics; neuromorphic circuit; neural network; leaky integrate-and-fire; spike-timing-dependent plasticity
Citation
Hogue, L. (2026). Small-Scale Analog Spiking Neural Network: Design and Simulation of an Analog Deep Neural Network. Electrical Engineering and Computer Science Undergraduate Honors Theses Retrieved from https://scholarworks.uark.edu/elcsuht/40
Included in
Electrical and Electronics Commons, VLSI and Circuits, Embedded and Hardware Systems Commons
