Hierarchical auto-associative polynomial convolutional neural networks
Patrick Martell · OhioLink ETD Center (Ohio Library and Information Network) · 2017
Convolutional neural networks (CNNs) lack ample methods to improve performance without either adding more input data, modifying existing data, or changing network design.This work seeks to add to the methods available that do not require more data or a trial and error approach to network design.This thesis seeks to demonstrate that a polynomial layer inserted into a CNN, compared to all other factors being equal has great potential to improve classification rates.There are some methods that seek to help fill the gap that this research also investigates an alternative solution.Most other methods in the similar problem space look at ways to improve performance of existing layers, such as modifying the type of pooling or activation functions.Also, methods discussed later, Dropout and DropConnect zero out nodes or connections, respectively, seeking to improve performance.This research focused on adding a new type of layer to typical CNNs, the polynomial layer.This layer adds a local connectivity to each of the perceptrons creating N connections up to the N th power of the initial value of the perceptron.This is done in either the convolutional portion or the fully connected portion, with the idea that the higher dimensionality allows for better description iii The help and guidance of Dr. Asari, Theus Aspiras, and the rest of the Vision Lab is immeasurable and I am incredibly grateful for their contribution.I would also like to thank the SMART Scholarship Program, who supported most of my Master of Science degree, providing me financial stability that has enabled me to focus on my research.