Deep symbolic regression
Discovering the underlying mathematical expressions describing a dataset is a core challenge for artificial intelligence. This is the problem of symbolic regression. Despite recent advances in training neural networks to solve complex tasks, deep learning approaches to symbolic regression are lacking. We propose a framework that combines deep learning with symbolic regression via a simple idea: use a large model to search the space of small models. More specifically, we use a recurrent neural network to emit a distribution over tractable mathematical expressions, and employ reinforcement learning to train the network to generate better-fitting expressions. Our algorithm significantly outperforms standard genetic programming-based symbolic regression in its ability to exactly recover symbolic expressions on a series of benchmark problems, both with and without added noise. More broadly, our contributions include a framework that can be applied to optimize hierarchical, variable-length objects under a black-box performance metric, with the ability to incorporate a priori constraints in situ.
Code (0)
등록된 구현이 없습니다.
Tasks
Deep LearningregressionSymbolic RegressionSimilar Papers 제목 키워드 기반
Elite Bases Regression: A Real-time Algorithm for Symbolic Regression
Symbolic regression is an important but challenging research topic in data mining. It can detect the underlying mathematical models. Genetic programming (GP) is one of the most popular methods for symbolic regression. Ho…
regressionSymbolic RegressionA Comparison of Recent Algorithms for Symbolic Regression to Genetic Programming
Symbolic regression is a machine learning method with the goal to produce interpretable results. Unlike other machine learning methods such as, e.g. random forests or neural networks, which are opaque, symbolic regressio…
regressionSymbolic RegressionSmooth Symbolic Regression: Transformation of Symbolic Regression into a Real-valued Optimization Problem
The typical methods for symbolic regression produce rather abrupt changes in solution candidates. In this work, we have tried to transform symbolic regression from an optimization problem, with a landscape that is so rug…
regressionSymbolic RegressionWhere are we now? A large benchmark study of recent symbolic regression methods
In this paper we provide a broad benchmarking of recent genetic programming approaches to symbolic regression in the context of state of the art machine learning approaches. We use a set of nearly 100 regression benchmar…
BenchmarkingBIG-bench Machine LearningregressionSymbolic RegressionNeural Symbolic Regression that Scales
Symbolic equations are at the core of scientific discovery. The task of discovering the underlying equation from a set of input-output pairs is called symbolic regression. Traditionally, symbolic regression methods use h…
regressionscientific discoverySymbolic Regression