A multi-core learning algorithm for Boolean neural networks

Author

Wang, D. ; Chaudhari, Narendra S.

Author_Institution

Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore

Volume

fYear

2003

fDate

20-24 July 2003

Firstpage

450

Abstract

We introduce a novel learning algorithm called multi-core learning (MCL) to construct a neural network for implementing a Boolean link training algorithm (BLTA) and expand-and-truncate learning (ETL). MCL needs a fewer hidden neurons. MCL also needs less number of operations for obtaining the connection weights and thresholds for hidden layer. We illustrate this advantage of our method (over ETL and BLTA) through an example.

Keywords

Boolean functions; learning (artificial intelligence); neural nets; Boolean function; Boolean like training algorithm; Boolean neural network; connection weight; expand and truncate learning; hidden layer; hidden neurons; learning algorithm; multicore learning; Boolean functions; Computer networks; Hamming distance; Hypercubes; Neural networks; Neurons; Pattern classification; Pattern recognition;

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.2003.1223388

Filename

1223388

Link To Document

https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=1918107