Title :
An analytical learning algorithm for the dendro-dendritic artificial neural network via linear programming
Author :
Ling, Bo ; Salam, Fathi M A
Author_Institution :
Dept. of Electr. Eng., Michigan State Univ., E. Lansing, MI, USA
Abstract :
An analytical learning algorithm to find the weight matrix of the dendro-dendritic neural network is presented. This learning algorithm utilizes linear programming to find all (necessarily) non-negative and small weights. A sufficient stability criterion is given, which guarantees all stored patterns to be asymptotically stable
Keywords :
learning (artificial intelligence); linear programming; matrix algebra; neural nets; analytical learning algorithm; dendro-dendritic neural network; linear programming; stored patterns; sufficient stability criterion; weight matrix; Algorithm design and analysis; Artificial neural networks; Hopfield neural networks; Linear programming; MOSFETs; Neural networks; Neurofeedback; Neurons; Stability criteria; Very large scale integration;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298830
