Minimisation methods for training feedforward neural networks

  title={Minimisation methods for training feedforward neural networks},
  author={Patrick van der Smagt},
  journal={Neural Networks},
-Mimmtsatlon methods for trammgfeedforward networks with back propagatton are compared Feedforward neural network trammg ts a special case of functlon mmtmtsatton, where no exphctt model o f the data ts assumed Therefore, and due to the htgh dlmenstonahty o f the data, hneartsatton of the trainmg problem through use o f orthogonal basts functtons is not destrable The focus ts on functton mmlmtsatton on any basts Quast-Newton and conJugate gradtent methods are revtewed, and the latter are shown… CONTINUE READING
Highly Influential
This paper has highly influenced 12 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
96 Citations
4 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 96 extracted citations


Publications referenced by this paper.
Showing 1-4 of 4 references

Adding stochastic search to conjugate gradient algorithms

  • K Hormk
  • Proceedings oJ the 3 rd International ConJerence…
  • 1992

A real - time neural robot controller

  • B. J. A Krose
  • Proceedings of the 1991 International Conference…
  • 1991

Similar Papers

Loading similar papers…