- Tytuł:
- Evolutionary learning of rich neural networks in the Bayesian model selection framework
- Autorzy:
-
Matteucci, M.
Spadoni, D. - Powiązania:
- https://bibliotekanauki.pl/articles/907642.pdf
- Data publikacji:
- 2004
- Wydawca:
- Uniwersytet Zielonogórski. Oficyna Wydawnicza
- Tematy:
-
sieć neuronowa
model Bayesa
algorytm genetyczny
Rich Neural Networks
Bayesian model selection
genetic algorithm
Bayesian fitness - Opis:
- In this paper we focus on the problem of using a genetic algorithm for model selection within a Bayesian framework. We propose to reduce the model selection problem to a search problem solved using evolutionary computation to explore a posterior distribution over the model space. As a case study, we introduce ELeaRNT (Evolutionary Learning of Rich Neural Network Topologies), a genetic algorithm which evolves a particular class of models, namely, Rich Neural Networks (RNN), in order to find an optimal domain-specific non-linear function approximator with a good generalization capability. In order to evolve this kind of neural networks, ELeaRNT uses a Bayesian fitness function. The experimental results prove that ELeaRNT using a Bayesian fitness function finds, in a completely automated way, networks well-matched to the analysed problem, with acceptable complexity.
- Źródło:
-
International Journal of Applied Mathematics and Computer Science; 2004, 14, 3; 423-440
1641-876X
2083-8492 - Pojawia się w:
- International Journal of Applied Mathematics and Computer Science
- Dostawca treści:
- Biblioteka Nauki
Artykuł