Title :
A serial complexity measure of neural networks
Author_Institution :
Dept. of Comput. Sci., Tel Aviv Univ., Israel
Abstract :
The most common methodology of neural network analysis is that of simulation since as of yet there is no common formal framework. Towards this end, one measure of serial algorithms is adopted, i.e., that of serial computational complexity. It is applied to the analysis of neural networks. Various networks are analyzed and their complexity is derived, thus providing insight as to their computational requirements
Keywords :
computational complexity; neural nets; computational complexity; computational requirements; neural networks; serial algorithms; serial complexity measure; Algorithm design and analysis; Computational complexity; Computational modeling; Computer networks; Computer science; Electronic mail; Hamming distance; Neural networks; Neurons; Read-write memory;
Conference_Titel :
Neural Networks, 1993., IEEE International Conference on
Conference_Location :
San Francisco, CA
Print_ISBN :
0-7803-0999-5
DOI :
10.1109/ICNN.1993.298687
