Implicant Network: an associative memory model

Author

Federici, Diego

Author_Institution

Dept. of Comput. & Inf. Sci., Norwegian Univ. of Sci. & Technol., Trondheim, Norway

Volume

4

fYear

2003

fDate

20-24 July 2003

Firstpage

3036

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;

fLanguage

English

Publisher

ieee

Conference_Titel

Neural Networks, 2003. Proceedings of the International Joint Conference on

ISSN

1098-7576

Print_ISBN

0-7803-7898-9

Type

conf

DOI

10.1109/IJCNN.2003.1224056

Filename

1224056