Item

Unsupervised Pre-Training by Evolving for Diverse Features

Donovan, Jordan
Citations
Altmetric:
License
License
Abstract
Deep neural networks (DNNs) excel at extracting complex patterns from data to solve complex, non-linear problems across several domains. The various initialization strategies utilized can greatly affect the accuracy of the resulting trained network and efficiency of the training process. We propose an evolutionary pre-training technique that initializes networks in a manner that optimizes toward orthogonality of feature activations in the convolutional filters of a CNN. Relative to randomly initialized parameters, this evolutionary pre-training improves the resulting accuracy of networks when training these convolutional filters on the image classification benchmark CIFAR-100.
Description
Date
2023-01-01
Student Status
Graduate
Journal Title
Journal ISSN
Volume Title
Type of presentation
Poster Presentation
Collections
UVM Student Research Conference
Show all metadata
Research Projects
Organizational Units
Journal Issue
Citation
URI
https://hdl.handle.net/20.500.14849/8579
DOI
Advisor(s)
Nicholas Cheney
Department
Program/Major
Computer Science
College/School
College of Engineering and Mathematical Sciences
Organization
item.page.researchcategory
Engineering and Math Science
Embedded videos