中文
相关论文

相关论文: A Transformer Model for Symbolic Regression toward…

200 篇论文

Symbolic Regression (SR) is a powerful technique for discovering interpretable mathematical expressions. However, benchmarking SR methods remains challenging due to the diversity of algorithms, datasets, and evaluation criteria. In this…

Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling de novo algorithm discovery without relying on human-written code. However, applying this paradigm to Transformer is…

机器学习 · 计算机科学 2026-03-20 Yifan Zhang , Wei Bi , Kechi Zhang , Dongming Jin , Jie Fu , Zhi Jin

Identifying governing equations for a dynamical system is a topic of critical interest across an array of disciplines, from mathematics to engineering to biology. Machine learning -- specifically deep learning -- techniques have shown their…

动力系统 · 数学 2026-05-07 Nibodh Boddupalli , Timothy Matchen , Jeff Moehlis

In a regression task, a function is learned from labeled data to predict the labels at new data points. The goal is to achieve small prediction errors. In symbolic regression, the goal is more ambitious, namely, to learn an interpretable…

机器学习 · 计算机科学 2025-06-25 Paul Kahlmeyer , Joachim Giesen , Michael Habeck , Henrik Voigt

Discovering a meaningful symbolic expression that explains experimental data is a fundamental challenge in many scientific fields. We present a novel, open-source computational framework called Scientist-Machine Equation Detector (SciMED),…

机器学习 · 计算机科学 2023-03-02 Liron Simon Keren , Alex Liberzon , Teddy Lazebnik

In nature, the behaviors of many complex systems can be described by parsimonious math equations. Automatically distilling these equations from limited data is cast as a symbolic regression process which hitherto remains a grand challenge.…

机器学习 · 计算机科学 2023-05-25 Yilong Xu , Yang Liu , Hao Sun

Symbolic regression discovers explicit, interpretable equations without assuming a functional form in advance. A Bayesian approach strengthens this through probability distributions over candidate expressions, thus quantifying uncertainty…

机器学习 · 计算机科学 2026-05-05 James Butterworth , Gevik Grigorian , Alejandro DiazDelaO

Symbolic regression (SR) aims to discover explicit mathematical expressions that explain observed data and is widely used in domains where interpretability is essential. Because interpretability requires expressions to reflect meaningful…

神经与进化计算 · 计算机科学 2026-05-18 Koki Ikeda , Masahiro Nomura , Ryoki Hamano

Symbolic regression (SR) is the problem of learning a symbolic expression from numerical data. Recently, deep neural models trained on procedurally-generated synthetic datasets showed competitive performance compared to more classical…

机器学习 · 计算机科学 2023-05-11 Pierre-Alexandre Kamienny , Guillaume Lample , Sylvain Lamprier , Marco Virgolin

Symbolic regression (SR) aims to find symbolic expressions that describe datasets. Due to its inherent interpretability, is a powerful paradigm for scientific discovery. Recent advances have expanded SR to describe related phenomena using a…

机器学习 · 计算机科学 2026-03-31 Viktor Martinek , Roland Herzog

Symbolic regression is a powerful technique that can discover analytical equations that describe data, which can lead to explainable models and generalizability outside of the training data set. In contrast, neural networks have achieved…

机器学习 · 计算机科学 2022-03-10 Samuel Kim , Peter Y. Lu , Srijon Mukherjee , Michael Gilbert , Li Jing , Vladimir Čeperić , Marin Soljačić

Regression analysis is used for prediction and to understand the effect of independent variables on dependent variables. Symbolic regression (SR) automates the search for non-linear regression models, delivering a set of hypotheses that…

机器学习 · 计算机科学 2025-04-09 Fabricio Olivetti de Franca , Gabriel Kronberger

Table structure recognition (TSR) aims to convert tabular images into a machine-readable format, where a visual encoder extracts image features and a textual decoder generates table-representing tokens. Existing approaches use classic…

计算机视觉与模式识别 · 计算机科学 2023-11-10 ShengYun Peng , Seongmin Lee , Xiaojing Wang , Rajarajeswari Balasubramaniyan , Duen Horng Chau

We propose a novel deep symbolic regression approach to enhance the robustness and interpretability of data-driven mathematical expression discovery. Our work is aligned with the popular DSR framework which focuses on learning a…

机器学习 · 计算机科学 2026-03-30 Zachary Bastiani , Robert M. Kirby , Jacob Hochhalter , Shandian Zhe

Symbolic regression is essential for deriving interpretable expressions that elucidate complex phenomena by exposing the underlying mathematical and physical relationships in data. In this paper, we present an advanced symbolic regression…

机器学习 · 计算机科学 2025-03-13 Sikai Huang , Yixin Berry Wen , Tara Adusumilli , Kusum Choudhary , Haizhao Yang

We introduce an Invertible Symbolic Regression (ISR) method. It is a machine learning technique that generates analytical relationships between inputs and outputs of a given dataset via invertible maps (or architectures). The proposed ISR…

机器学习 · 计算机科学 2024-05-14 Tony Tohme , Mohammad Javad Khojasteh , Mohsen Sadr , Florian Meyer , Kamal Youcef-Toumi

Compact symbolic expressions have been shown to be more efficient than neural network models in terms of resource consumption and inference speed when implemented on custom hardware such as FPGAs, while maintaining comparable…

机器学习 · 计算机科学 2025-02-11 Ho Fung Tsoi , Vladimir Loncar , Sridhara Dasu , Philip Harris

The high-energy physics community is investigating the potential of deploying machine-learning-based solutions on Field-Programmable Gate Arrays (FPGAs) to enhance physics sensitivity while still meeting data processing time constraints. In…

Symbolic Regression aims to automatically identify compact and interpretable mathematical expressions that model the functional relationship between input and output variables. Most existing search-based symbolic regression methods…

机器学习 · 计算机科学 2026-01-22 Jianwen Sun , Xinrui Li , Fuqing Li , Xiaoxuan Shen

Symbolic Regression (SR) can generate interpretable, concise expressions that fit a given dataset, allowing for more human understanding of the structure than black-box approaches. The addition of background knowledge (in the form of…

机器学习 · 计算机科学 2023-05-05 Charles Fox , Neil Tran , Nikki Nacion , Samiha Sharlin , Tyler R. Josephson