Novel Role Filler Generalization for Recurrent Neural Networks Using Working Memory-Based Indirection
Novel Role Filler Generalization for Recurrent Neural Networks Using Working Memory-Based Indirection
No Thumbnail Available
Date
2020-12-01
Authors
Mullinax, Chaning
Journal Title
Journal ISSN
Volume Title
Publisher
University Honors College Middle Tennessee State University
Abstract
Humans encounter and adapt to novel situations every day. However, adaptation
is not a trivial task to accomplish. In the field of machine learning, the statistical
underpinnings of established deep learning architectures make it difficult for these
architectures to handle certain types of novel situations. Previous research demonstrates
how computational models could better handle novel situations through indirection, an
idea inspired by the interaction between two regions of the human brain: the prefrontal
cortex and the basal ganglia. This thesis demonstrates that combining the indirection
model with deep learning methods outperforms current architectures.
Description
Keywords
College of Basic and Applied Sciences,
Machine Learning,
Artificial intelligence,
Indirection,
Working Memory,
Generalization,
Neural Networks,
Recurrent Neural Networks