A dynamic node architecture scheme for backpropagation neural networks [electronic resource].
- Washington, D.C. : United States. Dept. of Energy, 1991.
Oak Ridge, Tenn. : Distributed by the Office of Scientific and Technical Information, U.S. Dept. of Energy.
- Physical Description:
- Pages: (7 pages) : digital, PDF file
- Additional Creators:
- Ames Laboratory
United States. Department of Energy
United States. Department of Energy. Office of Scientific and Technical Information
- Typically, artificial neural network (ANN) training schemes require network architectures to be set before training. However, the Teaming speed and generalization characteristics of ANNs are dependent on their architectures. Thus, the viability of a specific architecture can only be evaluated after training. This work seeks to reduce the dependence of ANN capabilities on the preselection of network architectures. The present work describes an ANN dynamic node architecture (DNA) scheme which determines the appropriate number of nodes for a given network by defining an importance function which assigns an importance to each node in the network. Optimizing the network architecture becomes part of the training objective. The backpropagation learning algorithm has been implemented with this new DNA scheme.
- Published through SciTech Connect.
ANNIE '91: artificial neural networks in engineering conference, St. Louis, MO (United States), 10-13 Nov 1991.
Bartlett, E.; Basu, A.
- Funding Information:
View MARC record | catkey: 14357894