Risk assessment of axillary lymph node metastases in early breast cancer patients using the maximum entropy network
Poh Lian Choong, J.S. deSilva, H.J.S. Dawkins, P. Robbins, Jennet M. Harvey, G. F. Sterrett, J. M. Papadimitriou, Yianni Attikiouzel · 2002
Describes an artificial neural network (ANN) architecture for constructing maximum entropy (MaxEnt) models based on discrete distributions. Entropy is maximized by a partition function method involving the use of Lagrange multipliers which is capable of implementation by an ANN architecture. The maximum entropy network (MaxEN), consists of a training module and a testing module of interconnected processing elements. The practical use of the MaxEN network is illustrated with an application in the clinical management of early breast cancer patients.>