Feature detection networks in pattern recognition
In some pattern recognition problems a large number of patterns may be decomposed into a small set of subpatterns which can reconstitute each of the patterns. The use of such features can result in an economical recognition network. In such cases the pattern set may have an inherent hierarchical structure which can be incorporated in a layered logical network. An algorithm is presented which uses a training set of patterns to determine this structure. The subpatterns, termed features, are generated sequentially through an adaptive process of weight alteration in a neural network as each pattern is iteratively presented. A measure of 'relatedness' of a set of points is utilized to decide which subset of points associated with these sets of weights represents useful information and should be selected as a feature. Experimental results indicate the potential of the algorithm in organizing a recognition network to correspond to the information structure of the pattern set. (Author).
What people are saying - Write a review
We haven't found any reviews in the usual places.
Statement of the Problem
Weight Adaptive Techniques and Feature Generation
Measure of Relatedness in the Determination of Features
Sequential Alteration of the Pattern Set and Obtaining
Precise Mathematical Description of the Algorithm