Rowan University
An Empirical Study on the Efficacy of Evolutionary Algorithms for Automated Neural Architecture Search
Abstract
dc:description.abstractThe configuration and architecture design of neural networks is a time consuming process that has been shown to provide significant training speed and prediction improvements. Traditionally, this process is done manually, but this requires a large amount of expert knowledge and significant investment of labor. As a result it is beneficial to have automated ways to optimize model architectures. In this thesis, we study the use of evolutionary algorithm for neural architecture search (NAS). Moreover, we investigate the effect of integrating evolutionary NAS into deep reinforcement learning to learn control policy for ATARI game playing. Empirical classification results on the NASBench image dataset using different population selection and drop methods for the evolutionary NAS are presented to validate the usefulness of simple evolutionary algorithms in optimizing neural architectures, showing that even basic evolutionary algorithms are a well performing and easy to use approach. We also show the feasibility of using evolutionary NAS to extract good features that can improve the pong game playing score when the computational resource is limited.
Degree
thesis:*- Name thesis:degree_name
- M.S. Computer Science
- Level thesis:degree_level
- Thesis
- Discipline thesis:degree_discipline
- Computer Science
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Cuccinello, Andrew D.
- Contributors dc:contributor
-
- Shen-Shyang Ho, Ph.D.
- Bo Sun, Ph.D.
- Ning Wang, Ph.D.
Subjects
dc:subject × 7Identifiers
dc:identifier.*- Repository record dc:identifier
- https://rdw.rowan.edu/etd/2964