paper-with-me

홈 › Papers

Learning Symbolic Expressions via Gumbel-Max Equation Learner Networks

2020-12-12 · Gang Chen

Most of the neural networks (NNs) learned via state-of-the-art machine learning techniques are black-box models. For a widespread success of machine learning in science and engineering, it is important to develop new NN architectures to effectively extract high-level mathematical knowledge from complex datasets. Motivated by this understanding, this paper develops a new NN architecture called the Gumbel-Max Equation Learner (GMEQL) network. Different from previously proposed Equation Learner (EQL) networks, GMEQL applies continuous relaxation to the network structure via the Gumbel-Max trick and introduces two types of trainable parameters: structure parameters and regression parameters. This paper also proposes a two-stage training process with new techniques to train structure parameters in both online and offline settings based on an elite repository. On 8 benchmark symbolic regression problems, GMEQL is experimentally shown to outperform several cutting-edge machine learning approaches.

📄 PDF Abstract BibTeX arXiv:2012.06921

Code (0)

등록된 구현이 없습니다.

Tasks

BIG-bench Machine LearningregressionSymbolic Regression

Similar Papers 제목 키워드 기반

A Data-Free Symbolic Regression Approach for Solving Equations

2026-06-05 · Sergei Garmaev, Vinay Sharma, Olga Fink arxiv

Many equations arising in science currently cannot be solved by available analytical techniques and are therefore solved numerically, without yielding explicit symbolic expressions. Existing symbolic regression approache…

Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search

2022-05-26 · Fangzheng Sun, Yang Liu, Jian-Xun Wang, Hao Sun

Nonlinear dynamics is ubiquitous in nature and commonly seen in various science and engineering disciplines. Distilling analytical expressions that govern nonlinear dynamics from limited data remains vital but challengin…

Symbolically Solving Partial Differential Equations using Deep Learning

2020-11-12 · Maysum Panju, Kourosh Parand, Ali Ghodsi

We describe a neural-based method for generating exact or approximate solutions to differential equations in the form of mathematical expressions. Unlike other neural methods, our system returns symbolic expressions that…

Deep Learning

A neural method for symbolically solving partial differential equations

2021-01-01 · Anonymous

We describe a neural-based method for generating exact or approximate solutions to differential equations in the form of mathematical expressions. Unlike other neural methods, our system returns symbolic expressions that…

Ontolearn-A Framework for Large-scale OWL Class Expression Learning in Python

2025-10-13 · Caglar Demir, Alkid Baci, N'Dah Jean Kouagou, Leonie Nora Sieger 외 arxiv

In this paper, we present Ontolearn-a framework for learning OWL class expressions over large knowledge graphs. Ontolearn contains efficient implementations of recent stateof-the-art symbolic and neuro-symbolic class exp…

Knowledge Graphs