Logical Networks for Feature Extraction

The extraction of features for the purpose of reconstituting a pattern set may be particularly useful in those cases where a large number of patterns can be decomposed into a relatively small set of sub-patterns. By the representation of pattern and feature sets as matrices, the concept of feature determination has been extended to multilevel features and the hierarchical organization of logical networks employing these features. An algorithm is presented to sequentially generate features by an adaptive process of altering weights in a network of thresholdlike logical elements. Experimental results indicate the potential of the algorithm in organizing a recognition network to correspond to the information structure of the pattern set.