All Outputs (3)

Approximation of chaotic shapes with tree-structured neural networks (1999)
Presentation / Conference Contribution
Andras, P. (1999, July). Approximation of chaotic shapes with tree-structured neural networks. Presented at IJCNN'99: International Joint Conference on Neural Networks, Washington, DC, USA

The approximation of highly irregular decision regions is a challenging problem in pattern recognition and classification. Existing neural networks require many neurons for approximating irregular decision regions. A new tree-structured neural networ... Read More about Approximation of chaotic shapes with tree-structured neural networks.

Efficient selection of the node parameters in RBF neural networks (1999)
Presentation / Conference Contribution
Andras, P. (1999, December). Efficient selection of the node parameters in RBF neural networks

Orthogonal RBF neural network approximation (1999)
Journal Article
Andras, P. (1999). Orthogonal RBF neural network approximation. Neural Processing Letters, 9, 141-151. https://doi.org/10.1023/A%3A1018621308457

The approximation properties of the RBF neural networks are investigated in this paper. A new approach is proposed, which is based on approximations with orthogonal combinations of functions. An orthogonalization framework is presented for the Gaussi... Read More about Orthogonal RBF neural network approximation.