Entropy maximization networks: an application to breast cancer prognosis

Describes two artificial neural network architectures for constructing maximum entropy models using multinomial distributions. The architectures presented maximize entropy in two ways: by the use of the partition function (which involves the solution of simultaneous polynomial equations), and by con...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on neural networks 1996-05, Vol.7 (3), p.568-577
Main Authors: Poh Lian Choong, deSilva, C.J.S., Dawkins, H.J.S., Sterrett, G.F.
Format: Article
Language:English
Subjects:
Accuracy
Artificial neural networks
Biological and medical sciences
Breast cancer
Entropy
Equations
Gynecology. Andrology. Obstetrics
Mammary gland diseases
Medical sciences
Metastasis
Multilayer perceptrons
Neural networks
Polynomials
Predictive models
Tumors
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Describes two artificial neural network architectures for constructing maximum entropy models using multinomial distributions. The architectures presented maximize entropy in two ways: by the use of the partition function (which involves the solution of simultaneous polynomial equations), and by constrained gradient ascent. Results comparing the convergence properties of these two architectures are presented. The practical use of these two architectures as a method of inference is illustrated by an application to the prediction of metastases in early breast cancer patients. To assess the predictive accuracy of the maximum entropy models, we compared the results with those obtained by the use of the multilayer perceptron and the probabilistic neural network.
ISSN:1045-9227
1941-0093
DOI:10.1109/72.501716