Journal Article10.1109/72.750570
Fast initialization for cascade-correlation learning
38
TL;DR: Empirical simulations show that the new method can significantly speed-up the cascade-correlation learning compared to the case where the candidate training is used, and the overall performance remained similar or was even better than with the candidateTraining.
read more
Abstract: Weight initialization in cascade-correlation learning is considered. Most of the previous studies use the so called candidate training to deal with the initialization problem in the cascade-correlation learning. There several candidate hidden units are first trained, and then the one yielding the best value for the covariance criterion is installed to the network. In case there are many candidate units to be trained, the total computational cost of the training can become very large. Here we consider a new approach for weight initialization in cascade-correlation learning. The proposed method is based on the concept of stepwise regression. Empirical simulations show that the new method can significantly speed-up cascade-correlation learning compared to the case where the candidate training is used. Moreover, the overall performance remained similar or was even better than with the candidate training.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A New Adaptive Merging and Growing Algorithm for Designing Artificial Neural Networks
Md. Monirul Islam,A. Sattar,Faijul Amin,Xin Yao,Kazuyuki Murase +4 more
- 01 Jun 2009
TL;DR: The proposed adaptive merging and growing algorithm, called AMGA, has been tested on a number of benchmark problems in machine learning and ANNs, and can design compact ANN architectures with good generalization ability compared to other algorithms.
Evaluation of constructive neural networks with cascaded architectures
TL;DR: Five different constructive neural network algorithms are investigated, of which four were methods found in the literature and one was the authors' own recently developed algorithm, which produces rather often the best performance level among the investigated algorithms.
43
An incremental framework based on cross-validation for estimating the architecture of a multilayer perceptron
TL;DR: The MOST (Multiple Operators using Statistical Tests) framework that incrementally modifies the structure and checks for improvement using cross-validation is proposed and shows that MOST variants generally find simpler networks having lower or comparable error rates than DNC and CC.
The constraint based decomposition (CBD) training architecture
TL;DR: The Constraint Based Decomposition is shown to be able to solve complicated problems in a simple, fast and reliable manner and provides the second best average accuracy on the problems tested as well as the best reliability (the lowest standard deviation).
25
Mapping some basic functions and operations to multilayer feedforward neural networks for modeling nonlinear dynamical systems and beyond
TL;DR: This study examines linear sums of sigmoidal functions as a means to construct approximations to various nonlinear functions including reciprocal, absolute value, the product of absolute value and first-order polynomial, exponential, truncated sinc, Mexican hat, and Gaussian functions as well as the four elementary arithmetic operations.
23
References
•Book
Neural Networks: A Comprehensive Foundation
Simon Haykin
- 16 Jul 1998
TL;DR: Thorough, well-organized, and completely up to date, this book examines all the important aspects of this emerging technology, including the learning process, back-propagation learning, radial-basis function networks, self-organizing systems, modular networks, temporal processing and neurodynamics, and VLSI implementation of neural networks.
•Book
Digital Communications
John G. Proakis
- 01 Jan 1983
TL;DR: This month's guest columnist, Steve Bible, N7HPR, is completing a master’s degree in computer science at the Naval Postgraduate School in Monterey, California, and his research area closely follows his interest in amateur radio.
27.7K
•Book
Practical Methods of Optimization
Roger Fletcher
- 01 Jan 2009
TL;DR: The aim of this book is to provide a Discussion of Constrained Optimization and its Applications to Linear Programming and Other Optimization Problems.
9.3K
A direct adaptive method for faster backpropagation learning: the RPROP algorithm
Martin Riedmiller,Heinrich Braun +1 more
- 28 Mar 1993
TL;DR: A learning algorithm for multilayer feedforward networks, RPROP (resilient propagation), is proposed that performs a local adaptation of the weight-updates according to the behavior of the error function to overcome the inherent disadvantages of pure gradient-descent.