EQL

By Subham S. Sahoo, Christoph H. Lampert, Georg Martius

Equation Learner, a neural network approach to symbolic regression

We present an approach to identify concise equations from data using a shallow neural network approach. In contrast to ordinary black-box regression, this approach allows understanding functional relations and generalizing them from observed data to unseen parts of the parameter space.

• Paper: Learning equations for extrapolation and control

• Autonomous Learning Group at Max Planck Institue for Intelligent Systems, Tübingen, Germany: Website: al.is.mpg.de

Theano implementation:

• See the subdirectory EQL-DIV-ICML for the Theano code implementing the EQL-Division model.

Tensorflow implementation:

• Go to EQL_Tensorflow repository.

Citation

@inproceedings{sahoo2018learning,
  title={Learning equations for extrapolation and control},
  author={Sahoo, Subham and Lampert, Christoph and Martius, Georg},
  booktitle={International Conference on Machine Learning},
  pages={4442--4450},
  year={2018},
  organization={Pmlr}
}