Title :
Neural network super architectures
Author :
McMormack, C. ; Doherty, James
Author_Institution :
Dept. of Comput. Sci., Univ. Coll. Cork, Ireland
Abstract :
The influence of the initial architecture of a neural network on its learning ability is examined. Various architectural traits are combined in order to form a set of permutations of architectures each of which is trained for a benchmark problem. The results are compared to the original architectures of the benchmark problem. It can be observed from the results of the experiments that there exists a set of suitable architectures for each problem and in these sets certain ´super´ architectures can be identified which produce the best result for the problem.
Keywords :
learning (artificial intelligence); neural net architecture; learning ability; neural network super architectures; Backpropagation; Computer architecture; Computer science; Educational institutions; Measurement standards; Neural networks; Neurons;
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.1993.713917