Title :
Matrix realisations of multilayer perceptron ANN
Author :
Chidzonga, It F.
Author_Institution :
Dept. of Electr. Eng., Zimbabwe Univ., Harare, Zimbabwe
Abstract :
The backpropagation neural network training algorithm is formulated via matrix transformations as opposed to the usual indexed algebraic scalar approach. This formulation allows for easy visualisation and understanding of error propagation and the consequent weight adjustment. The so configured network can be readily unravelled for further study if required. Illustrative results on simple and concise Matlab simulation are presented
Keywords :
backpropagation; matrix algebra; multilayer perceptrons; neural net architecture; Matlab simulation; backpropagation neural network training algorithm; error propagation; matrix realisations; matrix transformations; multilayer perceptron ANN; multilayer perceptron architecture; visualisation; weight adjustment; Artificial neural networks; Error correction; Filtering; Neural networks;
Conference_Titel :
Communications and Signal Processing, 1997. COMSIG '97., Proceedings of the 1997 South African Symposium on
Conference_Location :
Grahamstown
Print_ISBN :
0-7803-4173-2
DOI :
10.1109/COMSIG.1997.630006
