zbMATH — the first resource for mathematics

Mathematical programming in neural networks. (English) Zbl 0789.90053
Summary: This paper highlights the role of mathematical programming, particularly linear programming, in training neural networks. A neural network description is given in terms of separating planes in the input space that suggests the use of linear programming for determining these planes. A more standard description in terms of a mean square error in the output space is also given, which leads to the use of unconstrained minimization techniques for training a neural network. The linear programming approach is demonstrated by a brief description of a system for breast cancer diagnosis that has been in use for the last four years at a major medical facility.

90C05 Linear programming
92B20 Neural networks for/in biological studies, artificial life and related topics
neural networks
Full Text: DOI