Title
A systematic and effective supervised learning mechanism based on Jacobian rank deficiency.
Abstract
Most neural network applications rely on the fundamental approximation property of feedforward networks. Supervised learning is a means of implementing this approximate mapping. In a realistic problem setting, a mechanism is needed to devise this learning process based on available data, which encompasses choosing an appropriate set of parameters in order to avoid overfitting, using an efficient learning algorithm measured by computation and memory complexities, ensuring the accuracy of the training procedures as measured by the training error, and testing and cross-validation for generalization. We develop a comprehensive supervised learning algorithm to address these issues. The algorithm combines training and pruning into one procedure by utilizing a common observation of Jacobian rank deficiency in feedforward networks. The algorithm not only reduces the training time and overall complexity but also achieves training accuracy and generalization capabilities comparable to more standard approaches. Extensive simulation results are provided to demonstrate the effectiveness of the algorithm.
Year
DOI
Venue
1998
10.1162/089976698300017610
Neural Computation
Keywords
Field
DocType
jacobian rank deficiency,effective supervised learning mechanism,cross validation,computational complexity,neural networks,training data,neural network,testing,newton method,supervised learning,feedforward neural networks,approximation property,nonlinear optimization,nonlinear programming,overfitting,computation,learning artificial intelligence,generalization,computer networks
Online machine learning,Competitive learning,Stability (learning theory),Instance-based learning,Semi-supervised learning,Computer science,Supervised learning,Unsupervised learning,Artificial intelligence,Overfitting,Machine learning
Journal
Volume
Issue
ISSN
10
4
0899-7667
Citations 
PageRank 
References 
5
1.26
7
Authors
2
Name
Order
Citations
PageRank
Guian Zhou1102.37
Jennie Si274670.23