Title :
Implicant Network: an associative memory model
Author_Institution :
Dept. of Comput. & Inf. Sci., Norwegian Univ. of Sci. & Technol., Trondheim, Norway
Abstract :
The Implicant Network is a neural network model capable of storing an arbitrary boolean function F : {0, 1}n → {0, 1}. The difference from previous one-shot learning models is that the training algorithm compresses the positive set online with linear time and space requirements. The algorithm works by building a Sum Of Products (SOP) representation of the positive set as it is presented to the network. Since the minimum coverage of implicants is an NP-hard problem, the compression rate is not optimal at first but it is shown to increase rapidly as the positive set is shown over again.
Keywords :
Boolean functions; computational complexity; content-addressable storage; learning (artificial intelligence); neural nets; Implicant Network; NP-hard problem; boolean function; compression rate; neural network model; sum of products representation; training algorithm; Animals; Associative memory; Autonomous agents; Boolean functions; Computer networks; Coordinate measuring machines; Humans; Information science; NP-hard problem; Neural networks;
Conference_Titel :
Neural Networks, 2003. Proceedings of the International Joint Conference on
Print_ISBN :
0-7803-7898-9
DOI :
10.1109/IJCNN.2003.1224056
