Method for weighting multiple example studying features based on master space classifying criterion

Abstract

The invention discloses a method for weighting multiple example studying features based on a master space classifying criterion. The realization scheme of the method comprises three steps of initializing a positive package representative example and a negative package representative example, building a problem to be optimized, and updating three kinds of unknown variables of the problem to be optimized. A representative example which can right express the category mark of a package in a positive package is found by adopting a heuristic search method, so that the problem of the fuzzification of the category mark of the example in the positive package is solved; repeated iteration is performed by adopting a coordinate rising method, so that the problem to be optimized can be converged into a local optimum solution; a relative weight is given according to the size of the contribution of each feature to recognition, and compared with the method of using original data for recognition, when the data which are weighted by features are used for recognition, higher recognition precision can be obtained.

Description

technical field [0001] The invention relates to a method for feature weighting of multi-example learning data based on a large-interval classification criterion, in particular to a data preprocessing method that assigns higher weights to effective discriminant features and lower weights to noise and redundant features method. This method can automatically weight each feature according to its contribution to recognition, and then recognize the weighted data to improve the recognition accuracy of multi-instance learning. Background technique [0002] Multi-instance learning is an important branch in the field of artificial intelligence. The sample it processes is not a single example, but a package, that is, a collection of a series of examples, and only the category label of the package is known. The category label of the example in the package is unknown. If a bag contains at least one positive example, the bag is marked as a positive bag, otherwise it is marked as a negat...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the lack of an effective feature weighting method in the existing multi-instance learning field, the present invention provides a multi-instance learning feature weighting method based on a large interval classification criterion