Date of Award

Spring 5-1-2023

Level of Access Assigned by Author

Open-Access Thesis

Degree Name

Doctor of Philosophy (PhD)


Computer Science


Roy Turner

Second Committee Member

James Fastook

Third Committee Member

Phillip Dickens

Additional Committee Members

David Hiebeler

Bruce Segee


Dendrites are root-like extensions from the neuron cell body and have long been thought to serve as the predominant input structures of neurons. Since the early twentieth century, neuroscience research has attempted to define the dendrite’s contribution to neural computation and signal integration. This body of experimental and modeling research strongly indicates that dendrites are not just input structures but are crucial to neural processing. Dendritic processing consists of both active and passive elements that utilize the spatial, electrical and connective properties of the dendritic tree.

This work presents a neuron model based around the structure and properties of dendrites. This research assesses the computational benefits and requirements of adding dendrites to a spiking artificial neuron model. A list of the computational properties of actual dendrites that have shaped this work is given. An algorithm capable of generating and training a network of dendritic neurons is created as an investigative tool through which computational challenges and attributes are explored.

This work assumes that dendrites provide a necessary and beneficial function to biological intelligence (BI) and their translation into the artificial intelligence (AI) realm would broaden the capabilities and improve the realism of artificial neural network (ANN) research. To date there have been only a few instances in which neural network-based AI research has ventured beyond the point neuron; therefore, the work presented here should be viewed as exploratory. The contribution to AI made by this work is an implementation of the artificial dendritic (AD) neuron model and an algorithm for training AD neurons with spatially distributed inputs with dendrite-like connectivity.

Files over 10MB may be slow to open. For best results, right-click and select "save as..."