This research would not had been possible but for the guidance and support of Dr. Michael T. Manry. His continued encouragement, willingness to listen and co-operate in an informal manner go beyond words. I owe sincere thanks to him. Special thanks go to other committee members Dr. Jack Fitzer and Dr. David P. Klemer for reviewing my work. I thank the past and present members of the Image processing and Neural Networks laboratory for providing a friendly atmosphere to work. I thank my father and mother for their support and encouragement throughout my career. I am deeply indebted to them. I thank my brothers and sister who had been a constant source of inspiration from miles away throughout my graduate program. Also, I thank my friends for the intangible help they had contributed towards the completion of this work. iv
|
2140
|
Learning Internal Representations by Error Propagation
– Rumelhart, Hinton, et al.
- 1986
|
|
904
|
Practical optimization
– Gill, Murray, et al.
- 1981
|
|
529
|
Approximation by superposition of a sigmoidal function
– Cybenko
- 1989
|
|
524
|
Networks for approximation and learning
– Poggio, Girosi
- 1990
|
|
483
|
The organization of behavior
– Hebb
- 1949
|
|
389
|
The perceptron: A probabilistic model for information storage and organization in the brain
– Rosenblatt
- 1958
|
|
366
|
Beyond Regression: New Tools for Prediction and Analysis
– Werbos
- 1974
|
|
363
|
Perceptrons : An Introduction to Computational Geometry
– Papert
- 1969
|
|
289
|
Identification and Control of Dynamical Systems Using Neural Networks
– Narendra, Parthasarathy
- 1990
|
|
209
|
Radial basis functions for multivariable interpolation: A review. In Algorithms for Approximation
– Powell
- 1987
|
|
145
|
Adaptive Pattern Recognition and Neural Networks
– Pao
- 1989
|
|
143
|
Backpropagation Through Time: What It Does and How to Do it
– Werbos
- 1990
|
|
137
|
Nonlinear Signal Processing Using Neural Networks
– Lapedes, Farber
- 1987
|
|
109
|
Bidirectional associative memories
– Kosko
- 1988
|
|
96
|
Function minimization by conjugate gradients
– Fletcher, Reeves
- 1964
|
|
90
|
Statistical pattern recognition with neural network: Benchmarking studies
– Kohonen, Barna, et al.
- 1988
|
|
57
|
Boltzmann machines: Constraint satisfaction networks that learn
– Hinton, Sejnowski, et al.
- 1984
|
|
55
|
Theory of the backpropagation neural network
– Hecht-Nielsen
- 1989
|
|
53
|
Kolmogorov mapping neural network existence theorem
– Hecht-Nielsen
- 1987
|
|
41
|
Capabilities of three-layered perceptrons
– Irie, Miyake
- 1988
|
|
38
|
On the representation of continuous functions of many variables by superpositions of continuous functions of one variable and addition
– Kolmogorov
- 1957
|
|
33
|
T.: ‘An introduction to neural computing
– KOHONEN
|
|
30
|
Optimization for training neural nets
– Barnard
- 1992
|
|
26
|
Universal Approximation Using Feedforward Networks with Nonsigmoid Hidden Layer Activation Functions
– Stinchcombe
- 1989
|
|
17
|
Nonlinear system modeling based on the Wiener theory
– Schetzen
- 1981
|
|
15
|
Introduction to Neural and Cognitive Modeling
– Levine
- 1998
|
|
15
|
A simple method to derive bounds on the size and to train multilayer neural networks
– Sartori, Antsaklis
- 1991
|
|
13
|
Vandermonde determinant and Lagrange interpolation
– Chui, Lai
- 1987
|
|
12
|
Neural Network Architectures for Robotics Applications
– Kung, Hwang
- 1989
|
|
12
|
The 13th Problem of Hilbert
– Lorentz
- 1976
|
|
9
|
Neural Computing: Theory and Practice
– Wassermann
- 1989
|
|
8
|
Back-propagation Representation Theorem Using Power Series
– Chen, Manry
- 1990
|
|
7
|
An Introduction to Computing with Neural Networks
– Lippman
- 1987
|
|
7
|
Adaptive Resonance Theory: stable self-organization of neural recognition codes in response to arbitrary lists of input patterns
– Carpenter, Grossberg
- 1986
|
|
7
|
Counterpropagation networks
– Hecht-Nielson
- 1987
|
|
7
|
Conventional Modeling of the Multilayer Perceptron Using Polynomial Basis Functions
– Chen, Manry
- 1993
|
|
7
|
Hourly Load Forecasting by Neural Networks
– Khotanzad, Hwang, et al.
- 1993
|
|
6
|
On Haar's theorem concerning Chebyshev approximation problems having unique solutions
– Mairhuber
- 1956
|
|
6
|
Output Weight Optimization for the Multi-layer Perceptron
– Manry, Guan, et al.
- 1992
|
|
5
|
Methods of Real Analysis
– Goldberg
- 1976
|
|
5
|
Maximum likelihood estimation for direction of arrival using a nonlinear optimizing neural network
– Jelonek, Reilly
- 1990
|
|
4
|
Analyses and Design of Multi-Layer Perceptron Using Polynomial Basis Functions
– Chen
- 1991
|
|
3
|
et al., "A universal nonlinear filter, predictor and simulator which optimizes itself by a learning process
– Gabor
- 1961
|
|
3
|
On a remarkable discovery in the theory of canonical forms and of hyperdeterminants
– Sylvester
- 1904
|
|
3
|
une extension d’un théorème de Clebsch relatif aux courbes du quatrième degré
– Sylvester, “Sur
|
|
3
|
Neural Subnet Design by Direct Polynomial Mapping
– Rohani, Chen, et al.
- 1992
|
|
3
|
Constructive proof of efficient pattern storage in the multilayer perceptron
– Gopalakrishnan, Jiang, et al.
- 1993
|
|
2
|
Sopra le Funzioni che Dipendono da Altre Funzioni, Nota 1
– Volterra
|
|
2
|
A Fast Algorithm of Nonlinear Volterra Filtering
– Morhac
- 1991
|
|
2
|
and M.T.Manry, "Power Series Analysis of backpropagation neural networks
– Chen
- 1991
|
