| Date |
7-10-2009 |
| Time |
14:30 |
| Room/Location |
Sala conferenze DISI, 3 piano |
| Title |
Model complexity of neural networks and integral transforms |
| Speaker |
Vera Kurkova |
| Affiliation |
Institute of Computer Science, Academy of Sciences of Czech Republic, Prague |
| Link |
https://www.disi.unige.it/index.php?eventsandseminars/seminars
|
| Abstract |
Model complexity of neural networks is investigated using tools from nonlinear approximation and integration theory. Estimates of network complexity are obtained from inspection of upper bounds on decrease of approximation errors in approximation of multivariable functions by networks with increasing numbers of units. The upper bounds are derived using integral transforms with kernels corresponding to various types of computational units. The results are applied to perceptron and Gaussian radial networks. |
