Pattern Recognition Letters
Geometrical synthesis of MLP neural networks
Neurocomputing
A Comparison of Methods for Learning of Highly Non-separable Problems
ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
Optimal design of neural nets using hybrid algorithms
PRICAI'00 Proceedings of the 6th Pacific Rim international conference on Artificial intelligence
Hi-index | 0.00 |
This paper presents a constructive training algorithm for supervised neural networks. The algorithm relies on a topological approach, based on the representation of the mapping of interest onto the binary hypercube of the input space. It dynamically constructs a two-layer neural network by involving successively binary examples. A convenient treatment of real-valued data is possible by means of a suitable real-to-binary codification. In the case of target functions that have efficient halfspace union representations, simulations show the constructed networks result optimized in terms of number of neurons