Constructive algorithms for structure learning in feedforward neural networks for regression problems
- 1 May 1997
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 8 (3) , 630-645
- https://doi.org/10.1109/72.572102
Abstract
In this survey paper, we review the constructive algorithms for structure learning in feedforward neural networks for regression problems. The basic idea is to start with a small network, then add hidden units and weights incrementally until a satisfactory solution is found. By formulating the whole problem as a state-space search, we first describe the general issues in constructive algorithms, with special emphasis on the search strategy. A taxonomy, based on the differences in the state transition mapping, the training algorithm, and the network architecture, is then presented.Keywords
This publication has 101 references indexed in Scilit:
- Connectionist projection pursuit regressionComputational Economics, 1994
- Optimization of the hidden unit function in feedforward neural networksNeural Networks, 1992
- Pattern classification using projection pursuitPattern Recognition, 1990
- Dynamic Node Creation in Backpropagation NetworksConnection Science, 1989
- Exploratory Projection PursuitJournal of the American Statistical Association, 1987
- Cross-Validation, the Jackknife, and the Bootstrap: Excess Error Estimation in Forward Logistic RegressionJournal of the American Statistical Association, 1986
- Projection Pursuit RegressionJournal of the American Statistical Association, 1981
- Generalized Cross-Validation as a Method for Choosing a Good Ridge ParameterTechnometrics, 1979
- Estimating the Dimension of a ModelThe Annals of Statistics, 1978
- A new look at the statistical model identificationIEEE Transactions on Automatic Control, 1974