Date of Award
2020
Document Type
Thesis
Degree Name
Bachelors
Department
Natural Sciences
First Advisor
Doucette, John
Area of Concentration
Computer Science
Abstract
In many Artificially Intelligent systems biological terms are used to describe particular concepts, or are used directly for inspiration. This project aims to create a more biologically plausible model of a neuron for use in a neural network which will evolve over generations to complete the task of balancing two poles on moving carts. This is attempted through the use of four-vectors and matrix multiplications and is ultimately unsuccessful at outperforming the original algorithm.
Recommended Citation
Works, Elan, "IMPLEMENTING MORE BIOLOGICALLY PLAUSIBLE NEURAL NETWORKS WITH MULTIPLE WEIGHTS IN NEAT" (2020). Theses & ETDs. 6017.
https://digitalcommons.ncf.edu/theses_etds/6017