Doctoral Dissertations
Keywords and Phrases
Deep Learning; Genetic Algorithm; Neural Architecture Search; Optimization
Abstract
"A long-standing goal in Deep Learning (DL) research is to design efficient architectures for a given dataset that are both accurate and computationally inexpensive. At present, designing deep learning architectures for a real-world application requires both human expertise and considerable effort as they are either handcrafted by careful experimentation or modified from a handful of existing models. This method is inefficient as the process of architecture design is highly time-consuming and computationally expensive.
The research presents an approach to automate the process of deep learning architecture design through a modeling procedure. In particular, it first introduces a framework that treats the deep learning architecture design problem as a systems architecting problem. The framework provides the ability to utilize novel and intuitive search spaces to find efficient architectures using evolutionary methodologies. Secondly, it uses a parameter sharing approach to speed up the search process and explores its limitations with search space. Lastly, it introduces a multi-objective approach to facilitate architecture design based on hardware constraints that are often associated with real-world deployment.
From the modeling perspective, instead of designing and staging explicit algorithms to process images/sentences, the contribution lies in the design of hybrid architectures that use the deep learning literature developed so far. This approach enjoys the benefit of a single problem formulation to perform end-to-end training and architecture design with limited computational resources"--Abstract, page iii.
Advisor(s)
Dagli, Cihan H., 1949-
Committee Member(s)
Qin, Ruwen
Kwasa, Benjamin J.
Yin, Zhaozheng
Wunsch, Donald C.
Department(s)
Engineering Management and Systems Engineering
Degree Name
Ph. D. in Systems Engineering
Publisher
Missouri University of Science and Technology
Publication Date
Spring 2020
Pagination
xi, 80 pages
Note about bibliography
Includes bibliographic references (pages 77-79).
Rights
© 2020 Ram Deepak Gottapu, All rights reserved.
Document Type
Dissertation - Open Access
File Type
text
Language
English
Thesis Number
T 11677
Electronic OCLC #
1164717843
Recommended Citation
Gottapu, Ram Deepak, "Computational model for neural architecture search" (2020). Doctoral Dissertations. 2866.
https://scholarsmine.mst.edu/doctoral_dissertations/2866