Mathematical models of diagnostics and forecasting in medicine and biology

The article considers the model of training the diagnosis on precedents on the basis of methods of pattern recognition and settings layered neural networks. It is shown that in this case the problem is reduced to construction of structures, generalizing the notion of solution of a system of linear inequalities. Justification of the proposed methods is given in the article. These methods are applied to problems of medical diagnostics and to the simulation of the empirical regularities.