Title :
Improved trinary associative memory for character recognition
Author :
Ahmed, Farid ; Awwal, A.A.S. ; Chen, C. L Philip
Author_Institution :
Comput. Sci. & Eng. Dept., Wright State Univ., Dayton, OH, USA
Abstract :
Character recognition by a trinary associative memory (TAM) neural network model is investigated. Three different inner product thresholding schemes, namely, zero plus average thresholding, arithmetic mean thresholding, and a novel adaptive thresholding are examined. It was shown by a simulation that the novel threshold prescription scheme with the permanent inhibition scheme enhanced the convergence as well as storage capacity of the inner product associative memory
Keywords :
character recognition; content-addressable storage; neural nets; adaptive thresholding; arithmetic mean thresholding; character recognition; convergence; ferroelectric liquid crystal spatial light modulator; neural network model; simulation; storage capacity; trinary associative memory; zero plus average thresholding; Arithmetic; Associative memory; Character recognition; Computer science; Convergence; Information retrieval; Neural networks; Optical character recognition software; Pattern recognition; Vectors;
Conference_Titel :
Aerospace and Electronics Conference, 1992. NAECON 1992., Proceedings of the IEEE 1992 National
Conference_Location :
Dayton, OH
Print_ISBN :
0-7803-0652-X
DOI :
10.1109/NAECON.1992.220487
