Recurrent neural networks: Architecture, algorithms and applications

Author

Xindi Cai

Abstract

“Recurrent neural networks (RNN) attract considerable interest in computational intelligence because of their superior power in processing spatio-temporal data and time- varying signals. In this research, we analyze how the architecture and training algorithm affect the dynamic properties of RNN. Proofs are presented to show that different transfer functions and biases can influence the system convergence to desired outputs in certain models. We demonstrate the advantages and limitations of gradient-based training algorithms, Recurrent Back Propagation (RBP) and Back Propagation through Time (BPTT). Evolutionary Algorithm (EA) is discussed for its global search process and non-gradient adaptation. A cellular Simultaneous Recurrent Network (SRN) computer Go player design illustrates the unique ability of function approximation for dynamic programming"--Abstract, page iii.

Advisor(s)

Wunsch, Donald C.

Committee Member(s)

Pottinger, Hardy J., 1944-
St. Clair, Daniel C.

Department(s)

Electrical and Computer Engineering

Degree Name

M.S. in Computer Engineering

Comments

The author gratefully acknowledges financial support from the following sources: (i) National Science Foundation; (ii) Sandia National Laboratories.

Publisher

University of Missouri--Rolla

Publication Date

Spring 2002

Pagination

viii, 38 pages

Note about bibliography

Includes bibliographical references (pages 33-37).

Rights

© 2002 Xindi Cai, All rights reserved.

Document Type

Thesis - Restricted Access

File Type

text

Language

English

Subject Headings

Neural networks (Computer science)

Thesis Number

T 8041

Print OCLC #

50231713

Recommended Citation

Cai, Xindi, "Recurrent neural networks: Architecture, algorithms and applications" (2002). Masters Theses. 2136.
https://scholarsmine.mst.edu/masters_theses/2136