A Mathematical Exploration of Neural Networks Using Sparsity, Entropy, and Multi-Valued Neurons

dc.contributor.advisorKunze, Herb
dc.contributor.advisorLevere, Kim
dc.contributor.authorBoreland, Bryson
dc.date.accessioned2023-05-08T15:12:44Z
dc.date.available2023-05-08T15:12:44Z
dc.date.copyright2023-05
dc.date.created2023-04-14
dc.degree.departmentDepartment of Mathematics and Statisticsen_US
dc.degree.grantorUniversity of Guelphen
dc.degree.nameDoctor of Philosophyen_US
dc.degree.programmeMathematics and Statisticsen_US
dc.description.abstractArtificial neural networks (ANN) are a major component of the artificial intelligence (AI) community that were designed based on the present understanding of their counterpart: the biological neuron. ANNs involve many different disciplines including mathematics, statistics, computer science, and engineering. The complexity of the different constructions of neural networks makes analytical mathematical work next to impossible and as a result computation and simulation are the methods used to study them. Our mathematical work focusses on two aspects. First, performance improvements through the inclusion of (generally small) perturbation terms, mathematically linked to the notions of sparsity and entropy, to the cost or objective function of the network. The formulation naturally fits in the realm of multicriteria decision making and is practically linked to overfitting. Overfitting is a common problem that is faced when dealing with neural networks, especially as computers continue to get more powerful, and we have the capability to train larger networks with many free parameters. As a result there is a pressing need to develop and explore different techniques to reduce overfitting. Loosely speaking, the thesis work suggests that the inclusion of either a sparsity criterion or an entropy criterion gives performance improvement, and the inclusion of both criteria gives a further improvement. Second, multi-valued neurons, particularly mathematical formulations in which the neurons are vector-valued, interval-valued, or convex-set-valued, are explored. Some potential applications are discussed and examples are explored.en_US
dc.identifier.urihttps://hdl.handle.net/10214/27531
dc.language.isoenen_US
dc.publisherUniversity of Guelphen
dc.rights.licenseAll items in the Atrium are protected by copyright with all rights reserved unless otherwise indicated.
dc.subjectArtificial neural networksen_US
dc.subjectMulti-valued neuronsen_US
dc.subjectPerturbation termsen_US
dc.subjectOverfittingen_US
dc.titleA Mathematical Exploration of Neural Networks Using Sparsity, Entropy, and Multi-Valued Neuronsen_US
dc.typeThesisen

Files

Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
Boreland_Bryson_202305_PhD.pdf
Size:
11.06 MB
Format:
Adobe Portable Document Format
Description: