Title :
Determining overlap of classes in the n-dimensional Boolean space
Author :
De Padua Braga, Antonio ; Aleksander, Igor
Author_Institution :
Dept. of Electr. Eng., Imperial Coll. of Sci., Technol. & Med., London, UK
fDate :
27 Jun-2 Jul 1994
Abstract :
This paper presents a solution to the problem of determining the distribution of the n-dimensional Boolean space in relation to two arbitrary patterns which are separated by a fixed distance h in such space. The estimation of such distribution allows the evaluation of the amount of overlap between the two corresponding r-spheres, which is a measure of the correlation between the classes determined by the patterns. This work is significant for applications in pattern recognition as well as for works on storage capacity and retrievability of patterns in Boolean neural networks
Keywords :
Boolean functions; content-addressable storage; correlation methods; neural nets; pattern classification; Boolean neural networks; class overlapping; correlation; n-dimensional Boolean space distribution; pattern recognition; pattern retrievability; sparse distributed memory; storage capacity; Codes; Educational institutions; Geometry; Information theory; Neural networks; Pattern recognition; Visualization;
Conference_Titel :
Neural Networks, 1994. IEEE World Congress on Computational Intelligence., 1994 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-1901-X
DOI :
10.1109/ICNN.1994.375050
