Improving neural networks for pattern recognition and function approximation

Improving neural networks for pattern recognition and function approximation

This thesis studies various issues related to artificial neural networks for pattern recognition and function approximation with the aim to enhance its capability and to improve its performance. It proposes a novel method for globally finding good minima and optimizing the Correct Classification Rat...

Full description

Saved in:
Bibliographic Details
Main Author: Zhang, Ximin
Other Authors: Chen, Yan Qiu
Format: Theses and Dissertations
Language:English
Published: 2008
Subjects:
DRNTU::Engineering::Electrical and electronic engineering::Electronic systems::Signal processing
DRNTU::Engineering::Computer science and engineering::Computing methodologies::Pattern recognition
Online Access:http://hdl.handle.net/10356/13130
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:This thesis studies various issues related to artificial neural networks for pattern recognition and function approximation with the aim to enhance its capability and to improve its performance. It proposes a novel method for globally finding good minima and optimizing the Correct Classification Rate(CCR), and a novel algorithm for network construction and weight initialization. The thesis also an-alyzes the fundamentals of Time-Delay Neural Network(TDNN) and presents an augmented TDNN (ATDNN) for frequency and scale invariant sequence classification.

Similar Items