K
K. Kalantri
Researcher at University of Maine
Publications - 5
Citations - 132
K. Kalantri is an academic researcher from University of Maine. The author has contributed to research in topics: Artificial neural network & Probabilistic neural network. The author has an hindex of 4, co-authored 5 publications receiving 128 citations.
Papers
More filters
Journal ArticleDOI
On the generalization ability of neural network classifiers
TL;DR: The proposed evaluation technique has been used to investigate the generalization ability of back propagation, radial basis function and probabilistic neural network (PNN) classifiers for three test problems.
Journal ArticleDOI
A probabilistic model for evaluation of neural network classifiers
TL;DR: A probabilistic input model is proposed to account for all possible input ranges and the expected value of a square error function over the defined input range is taken as a measure of generalization ability.
Journal ArticleDOI
A minimum error neural network (MNN)
TL;DR: The proposed minimum error neural network has shown improved performance and a major distinction between this network and other Gaussian based estimators is in the selection of covariance matrices.
Proceedings ArticleDOI
Improving the performance of probabilistic neural networks
TL;DR: It has been shown that the proposed technique improves the generalization ability of the PNN classifiers over the standard approach and can be applied to other Gaussian-based classifiers such as the radial basis functions.
Proceedings ArticleDOI
On the generalization ability of neural network classifiers
TL;DR: It has been shown that the boundaries of the MENN decision surface, in the sense of least mean square error, are equivalent to the boundaries obtained by the Bayes rule.