JEWLScholar@MTSU Repository

A Neurobiologically-inspired Deep Learning Framework for Autonomous Context Learning

Show simple item record

dc.contributor.advisor Phillips, Joshua L
dc.contributor.author Ludwig, David William
dc.date.accessioned 2020-11-16T20:02:22Z
dc.date.available 2020-11-16T20:02:22Z
dc.date.issued 2020
dc.identifier.uri https://jewlscholar.mtsu.edu/handle/mtsu/6320
dc.description.abstract Neurobiologically-inspired working memory models have managed to accurately demonstrate and explain our ability to rapidly adapt and alter our responses to the environment. However, the applications of these working memory models have been limited to reinforcement learning problems. Furthermore, the incorporation of contextual/switching mechanisms outside of the realm of working memory modeling for general-use cases has also been relatively unexplored. We present a new framework compatible with Tensorflow Keras enabling the straightforward integration of working memory-inspired mechanisms into typical neural network architectures. These mechanisms allow models to autonomously learn multiple tasks, statically or dynamically allocated. We also examine the generalization of the framework across a variety of multi-context supervised learning and reinforcement learning tasks. The resulting experiments successfully integrate these mechanisms with multilayer and convolutional neural network architectures. The diversity of problems solved demonstrates the framework’s generalizability across a variety of architectures and tasks.
dc.publisher Middle Tennessee State University
dc.source.uri http://dissertations.umi.com/mtsu:11360
dc.subject Context learning
dc.subject Deep learning
dc.subject Machine learning
dc.subject Neural networks
dc.subject Working memory
dc.subject Artificial intelligence
dc.subject Computer science
dc.title A Neurobiologically-inspired Deep Learning Framework for Autonomous Context Learning
dc.date.updated 2020-11-16T20:02:22Z
dc.language.rfc3066 en
dc.contributor.committeemember Barbosa, Salvador E
dc.contributor.committeemember Li, Cen
dc.thesis.degreelevel masters
dc.description.degree M.S.


Files in this item

This item appears in the following Collection(s)

Show simple item record

Search JEWLScholar@MTSU


Browse

My Account

Statistics