Kolmogorov learning for feedforward networks
2001
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:
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
11
References
6
Citations
NaN
KQI