Title :
Entropy maximization networks: an application to breast cancer prognosis
Author :
Choong, Poh Lian ; Desilva, Christopher J S ; Dawkins, H.J.S. ; Sterrett, Gregory F.
Author_Institution :
Dept. of Electr. & Electron. Eng., Western Australia Univ., Nedlands, WA, Australia
fDate :
5/1/1996 12:00:00 AM
Abstract :
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
Keywords :
convergence; inference mechanisms; maximum entropy methods; medical computing; multilayer perceptrons; neural net architecture; prediction theory; artificial neural network architectures; breast cancer prognosis; constrained gradient ascent; convergence properties; entropy maximization networks; inference; maximum entropy models; metastasis prediction; multilayer perceptron; multinomial distributions; partition function; predictive accuracy; probabilistic neural network; simultaneous polynomial equations; Accuracy; Artificial neural networks; Breast cancer; Entropy; Equations; Metastasis; Multilayer perceptrons; Neural networks; Polynomials; Predictive models;
Journal_Title :
Neural Networks, IEEE Transactions on
