Title :
Kolmogorov learning for feedforward networks
Author :
R. Neruda;A. Stedry;J. Drkosova
Author_Institution :
Inst. of Comput. Sci., Czechoslovak Acad. of Sci., Prague, Czech Republic
fDate :
6/23/1905 12:00:00 AM
Abstract :
We present a learning algorithm for feedforward neural networks that is based on Kolmogorov theorem concerning composition of a n-dimensional continuous function from a one-dimensional continuous functions. A thorough analysis of the algorithm time complexity is presented for its serial and parallel implementation.
Keywords :
"Neural networks","Clustering algorithms","Computer science","Feedforward neural networks","Algorithm design and analysis","Workstations","Computer networks","Quantum computing"
Conference_Titel :
Neural Networks, 2001. Proceedings. IJCNN ´01. International Joint Conference on
Print_ISBN :
0-7803-7044-9
DOI :
10.1109/IJCNN.2001.938995
