Constructive algorithms for structure learning in feedforward neural networks for regression problems

James Tin-Yau Kwok, Dit-Yan YeungIEEE Trans. Neural Networks 1997 · OpenReview

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.
BibTeX
@article{kwok1997constructive,
  author = {James Tin-Yau Kwok and Dit-Yan Yeung},
  title = {{Constructive algorithms for structure learning in feedforward neural networks for regression problems}},
  journal = {IEEE Trans. Neural Networks},
  year = {1997},
  url = {https://openreview.net/forum?id=6B0QlnZrn4},
}

Loading related content...

Figure