Model Complexity of Neural Networks and Integral Transforms

Authors: Věra Kůrková
Publication year: 2009
Publication type: Konferenční příspěvek (mezinárodní konf.)
Periodical: Artificial Neural Networks - ICANN 2009
Projects: Complexity of perceptron and kernel networks
Bibliographic citation: KŮRKOVÁ, Věra. Model Complexity of Neural Networks and Integral Transforms. In: ALIPPI, C., POLYCARPOU, M., PANAYIOTOU, C., ELLINAS, G., eds. Artificial Neural Networks - ICANN 2009. Berlin: Springer, 2009, S. 708-717. Lecture Notes in Computer Science, 5768. ISBN 978-3-642-04273-7
Dostupné z: doi:10.1007/978-3-642-04274-4_73
DOI: 10.1007/978-3-642-04274-4_73
ID: 328417

Abstract

Estimates of network complexity are derived using integral transforms with kernels corresponding to various types of computational units. The results are applied to perceptron networks.