On the Generalization Ability of Neural Network Classifiers

Authors:
M. T. Musavi;K. H. Chan;D. M. Hummels;K. Kalantri
Affiliations:
-;-;-;-
Venue:
IEEE Transactions on Pattern Analysis and Machine Intelligence
Year:
1994

Citing 6
Cited 6

Radial basis functions for multivariable interpolation: a review

Algorithms for approximation
Estimation of Classifier Performance

IEEE Transactions on Pattern Analysis and Machine Intelligence
Probabilistic neural networks

Neural Networks
Learning internal representations by error propagation

Parallel distributed processing: explorations in the microstructure of cognition, vol. 1
On the implementation of RBF technique in neural networks

ANNA '91 Proceedings of the conference on Analysis of neural network applications
Original Contribution: On the training of radial basis function classifiers

Neural Networks

Fuzzy expert systems architecture for image classification using mathematical morphology operators

Information Sciences—Informatics and Computer Science: An International Journal - Special issue: Intelligent information systems and applications
Optimization of the kernel functions in a probabilistic neural network analyzing the local pattern distribution

Neural Computation
Neural Learning from Unbalanced Data Using Noise Modeling

Proceedings of the 14th International conference on Industrial and engineering applications of artificial intelligence and expert systems: engineering of intelligent systems
Neural Learning from Unbalanced Data

Applied Intelligence
Independent residual analysis for temporally correlated signals

IWANN'03 Proceedings of the Artificial and natural neural networks 7th international conference on Computational methods in neural modeling - Volume 1
Probabilistic neural network with homogeneity testing in recognition of discrete patterns set

Neural Networks

Quantified Score

Hi-index	0.15

Visualization

Abstract

This correspondence presents a method for evaluation of artificial neural network (ANN) classifiers. In order to find the performance of the network over all possible input ranges, a probabilistic input model is defined. The expected error of the output over this input range is taken as a measure of generalization ability. Two essential elements for carrying out the proposed evaluation technique are estimation of the input probability density and numerical integration. A nonparametric method, which depends on the nearest M neighbors, is used to locally estimate the distribution around each training pattern. An orthogonalization procedure is utilized to determine the covariance matrices of local densities. A Monte Carlo method is used to perform the numerical integration. The proposed evaluation technique has been used to investigate the generalization ability of back propagation (BP), radial basis function (RBF) and probabilistic neural network (PNN) classifiers for three test problems.