Title :
Connectionist networks for binary bit-string multiplication
Author :
Sawhney, Samir ; Dudgeon, James E.
Author_Institution :
Dept. of Electr. Eng., Alabama Univ., Tuscaloosa, AL, USA
Abstract :
The connectionist learning technique of backpropagation is utilized to train a three-layer network to simulate the operation of a binary bit-string multiplier. It is shown that the network develops internal representations of a high quality, that allow it to generalize correctly to novel input patterns. The learning algorithm of N. Littlestohe (1987) is also used to train a network with a problem-specific architecture to realize a multiplier. The advantages and disadvantages of such an approach are discussed and a brief analysis of the results is presented
Keywords :
learning systems; neural nets; backpropagation; binary bit-string multiplication; connectionist learning technique; internal representations; problem-specific architecture; three-layer network; Algorithm design and analysis; Analytical models; Boolean functions; Computational modeling; Computer hacking; Computer networks; Delay; Input variables; Pattern analysis; Rain;
Conference_Titel :
Southeastcon '91., IEEE Proceedings of
Conference_Location :
Williamsburg, VA
Print_ISBN :
0-7803-0033-5
DOI :
10.1109/SECON.1991.147776
