Medizinische Universität Graz Austria/Österreich - Forschungsportal - Medical University of Graz
Gewählte Publikation:
SHR Neuro Krebs Kardio Lipid Stoffw Microb
Galicki, M; Leistritz, L; Zwick, EB; Witte, H.
Improving generalization capabilities of dynamic neural networks.
Neural Comput. 2004; 16(6):1253-1282
Doi: 10.1162/089976604773717603
Web of Science
PubMed
FullText
FullText_MUG
- Co-Autor*innen der Med Uni Graz
- Zwick Bernhard-Ernst
- Altmetrics:
- Dimensions Citations:
- Plum Analytics:
- Scite (citation analytics):
- Abstract:
- This work addresses the problem of improving the generalization capabilities of continuous recurrent neural networks. The learning task is transformed into an optimal control framework in which the weights and the initial network state are treated as unknown controls. A new learning algorithm based on a variational formulation of Pontrayagin's maximum principle is proposed. Under reasonable assumptions, its convergence is discussed. Numerical examples are given that demonstrate an essential improvement of generalization capabilities after the learning process of a dynamic network.
- Find related publications in this database (using NLM MeSH Indexing)
- Algorithms -
- Computer Simulation -
- Models, Neurological -
- Neural Networks (Computer) -