HONEST: a new high order feedforward neural network

A frequently voiced complaint regarding neural networks is that it is difficult to interpret the results of training in a meaningful way. The HONEST network is a new feedforward high order neural network (HONN) which not only allows a fuller degree of adaptability in the form of the nonlinear mapping than the sigma-pi model, but has a structure that can make it easier to understand how the network inputs come to be mapped into the network outputs. This structure also makes it easier to use external expert knowledge of the domain to examine the validity of the HONEST network solution and possible to reject some solutions. This is particularly important for embedded, failure-critical systems such as life-support systems. We have applied the HONEST network to the problem of forecasting the onset of diabetes using eight physiological measurements and genetic factors. We obtained a successful classification rate of 83% compared to a 76% rate that had been obtained by previous researchers.

[1]  A. G. Ivakhnenko,et al.  Polynomial Theory of Complex Systems , 1971, IEEE Trans. Syst. Man Cybern..

[2]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[3]  Sanjoy Mahajan,et al.  A Pattern Classification Approach to Evaluation Function Learning , 1988, Artif. Intell..

[4]  Kai-Fu Lee,et al.  The Development of a World Class Othello Program , 1990, Artif. Intell..

[5]  Stanley J. Farlow,et al.  Self-Organizing Methods in Modeling: Gmdh Type Algorithms , 1984 .

[6]  Venkat Venkatasubramanian,et al.  Solving the hidden node problem in networks with ellipsoidal units and related issues , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[7]  Mu-Chun Su,et al.  A novel class of neural networks with quadratic junctions , 1991, Conference Proceedings 1991 IEEE International Conference on Systems, Man, and Cybernetics.

[8]  A. M. Abdelbar.  Teaching the HONEST Neural Network to Judge the Strength of Othello Positions , 1996 .

[9]  Y. Abu-Mostafa.  Machines that Learn from Hints , 1995 .

[10]  Jacek M. Zurada,et al.  Introduction to artificial neural systems , 1992 .

[11]  Y.S. Abu-Mostafa.  An algorithm for learning from hints , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[12]  Richard S. Johannes,et al.  Using the ADAP Learning Algorithm to Forecast the Onset of Diabetes Mellitus , 1988 .

[13]  Geoffrey E. Hinton,et al.  A general framework for parallel distributed processing , 1986 .

[14]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .