A dynamic node architecture scheme for backpropagation neural networks
Conference
·
OSTI ID:6603686
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.
- Research Organization:
- Iowa State Univ. of Science and Technology, Ames, IA (United States)
- Sponsoring Organization:
- DOE; USDOE, Washington, DC (United States)
- DOE Contract Number:
- FG02-92ER75700
- OSTI ID:
- 6603686
- Report Number(s):
- CONF-9111215-2; ON: DE93010311
- Country of Publication:
- United States
- Language:
- English
Similar Records
A dynamic node architecture scheme for backpropagation neural networks
Backpropagation architecture optimization and an application in nuclear power plant diagnostics
Backpropagation architecture optimization and an application in nuclear power plant diagnostics
Conference
·
Mon Dec 30 23:00:00 EST 1991
·
OSTI ID:10142922
Backpropagation architecture optimization and an application in nuclear power plant diagnostics
Conference
·
Wed Mar 31 23:00:00 EST 1993
·
OSTI ID:10140175
Backpropagation architecture optimization and an application in nuclear power plant diagnostics
Conference
·
Thu Dec 31 23:00:00 EST 1992
·
OSTI ID:6551800