Use of a Multi-Layer Perceptron to Predict Malignancy in Ovarian Tumors

Herman Verrelst, Yves Moreau, Joos Vandewalle, Dirk Timmerman

NeurIPS 1997 pp. 978-984

/neurips/1997/verrelst1997neurips-use/

Abstract

This paper is concerned with the problem of Reinforcement Learn(cid:173) ing (RL) for continuous state space and time stocha.stic control problems. We state the Harnilton-Jacobi-Bellman equation satis(cid:173) fied by the value function and use a Finite-Difference method for designing a convergent approximation scheme. Then we propose a RL algorithm based on this scheme and prove its convergence to the optimal solution.

PDF NeurIPS Semantic Scholar

Cite

Text

Verrelst et al. "Use of a Multi-Layer Perceptron to Predict Malignancy in Ovarian Tumors." Neural Information Processing Systems, 1997.

Markdown

[Verrelst et al. "Use of a Multi-Layer Perceptron to Predict Malignancy in Ovarian Tumors." Neural Information Processing Systems, 1997.](https://mlanthology.org/neurips/1997/verrelst1997neurips-use/)

BibTeX

@inproceedings{verrelst1997neurips-use,
  title     = {{Use of a Multi-Layer Perceptron to Predict Malignancy in Ovarian Tumors}},
  author    = {Verrelst, Herman and Moreau, Yves and Vandewalle, Joos and Timmerman, Dirk},
  booktitle = {Neural Information Processing Systems},
  year      = {1997},
  pages     = {978-984},
  url       = {https://mlanthology.org/neurips/1997/verrelst1997neurips-use/}
}