Extrapolation and learning equations

G.S. Martius, C. Lampert, in:, 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings, International Conference on Learning Representations, 2017.

Conference Paper | Published | English
Department
Abstract
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.
Publishing Year
Date Published
2017-02-21
Proceedings Title
5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings
Conference
ICLR: International Conference on Learning Representations
Conference Location
Toulon, France
Conference Date
2017-04-24 – 2017-04-26
IST-REx-ID

Cite this

Martius GS, Lampert C. Extrapolation and learning equations. In: 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. International Conference on Learning Representations; 2017.
Martius, G. S., & Lampert, C. (2017). Extrapolation and learning equations. In 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. Toulon, France: International Conference on Learning Representations.
Martius, Georg S, and Christoph Lampert. “Extrapolation and Learning Equations.” In 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. International Conference on Learning Representations, 2017.
G. S. Martius and C. Lampert, “Extrapolation and learning equations,” in 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings, Toulon, France, 2017.
Martius GS, Lampert C. 2017. Extrapolation and learning equations. 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings. ICLR: International Conference on Learning Representations
Martius, Georg S., and Christoph Lampert. “Extrapolation and Learning Equations.” 5th International Conference on Learning Representations, ICLR 2017 - Workshop Track Proceedings, International Conference on Learning Representations, 2017.

Link(s) to Main File(s)
Access Level
OA Open Access

Export

Marked Publications

Open Data IST Research Explorer

Sources

arXiv 1610.02995

Search this title in

Google Scholar