Title :
On an optimal learning scheme for bidirectional associative memories
Author :
Shanmuk, K. ; Venkatesh, Y.V.
Author_Institution :
Comput. Vision & Artificial Intelligence Lab., Inst. of Sci., Bangalore, India
Abstract :
An optimal learning scheme is proposed for a class of bidirectional associative memories (BAMs). This scheme, based on the perceptron learning algorithm, is motivated by the inadequacies/incompleteness of the weighted learning by global optimization, as derived by Wang et al. (1993). It is shown that the new scheme has superior properties: (1) Convergence to the correct solution, when it exists; and (2) A larger basin of attraction for the given set of patterns.
Keywords :
content-addressable storage; convergence; learning (artificial intelligence); perceptrons; basin of attraction; bidirectional associative memories; convergence; optimal learning scheme; perceptron learning algorithm; weighted learning by global optimization; Artificial intelligence; Artificial neural networks; Computer vision; Convergence; Laboratories; Learning; Neural networks; Neurofeedback; Neurons; Pattern recognition;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.714273
