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 Subham S. Sahoo, Christoph H. Lampert, Georg Martius 2018
-
Autonomous Learning Group at Max Planck Institue for Intelligent Systems, Tübingen, Germany: Website: al.is.mpg.de
- See the subdirectory EQL-DIV-ICML for the Theano code implementing the EQL-Division model.
- go to EQL_Tensorflow repository