Extrapolation and learning equations Martius, Georg S Lampert, Christoph ; https://orcid.org/0000-0001-8622-7887 In classical machine learning, regression is treated as a black box process of identifying a suitable function from a hypothesis set without attempting to gain insight into the mechanism connecting inputs and outputs. In the natural sciences, however, finding an interpretable function for a phenomenon is the prime goal as it allows to understand and generalize results. This paper proposes a novel type of function learning network, called equation learner (EQL), that can learn analytical expressions and is able to extrapolate to unseen domains. It is implemented as an end-to-end differentiable feed-forward network and allows for efficient gradient based training. Due to sparsity regularization concise interpretable expressions can be obtained. Often the true underlying source expression is identified. International Conference on Learning Representations 2017 info:eu-repo/semantics/conferenceObject doc-type:conferenceObject text http://purl.org/coar/resource_type/c_5794 https://research-explorer.ista.ac.at/record/6841 Martius GS, Lampert C. Extrapolation and learning equations. In: <i>5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings</i>. International Conference on Learning Representations; 2017. eng info:eu-repo/semantics/altIdentifier/arxiv/1610.02995 info:eu-repo/semantics/openAccess