Neuro-Evolutionary Approach to Physics-Aware Symbolic Regression

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F25%3A00383571" target="_blank" >RIV/68407700:21730/25:00383571 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1145/3712256.3726434" target="_blank" >https://doi.org/10.1145/3712256.3726434</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1145/3712256.3726434" target="_blank" >10.1145/3712256.3726434</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Neuro-Evolutionary Approach to Physics-Aware Symbolic Regression

Popis výsledku v původním jazyce

Symbolic regression is a technique that can automatically derive analytic models from data. Traditionally, symbolic regression has been implemented primarily through genetic programming that evolves populations of candidate solutions sampled by genetic operators, crossover and mutation. More recently, neural networks have been employed to learn the entire analytical model, i.e., its structure and coefficients, using regularized gradient-based optimization. Although this approach tunes the model’s coefficients better, it is prone to premature convergence to suboptimal model structures. Here, we propose a neuro-evolutionary symbolic regression method that combines the strengths of evolutionary-based search for optimal neural network (NN) topologies with gradient-based tuning of the network’s parameters. Due to the inherent high computational demand of evolutionary algorithms, it is not feasible to learn the parameters of every candidate NN topology to the full convergence. Thus, our method employs a memory-based strategy and population perturbations to enhance exploitation and reduce the risk of being trapped in suboptimal NNs. In this way, each NN topology can be trained using only a short sequence of backpropagation iterations. The proposed method was experimentally evaluated on three real-world test problems and has been shown to outperform other NN-based approaches regarding the quality of the models obtained.

Název v anglickém jazyce

Neuro-Evolutionary Approach to Physics-Aware Symbolic Regression

Popis výsledku anglicky

Symbolic regression is a technique that can automatically derive analytic models from data. Traditionally, symbolic regression has been implemented primarily through genetic programming that evolves populations of candidate solutions sampled by genetic operators, crossover and mutation. More recently, neural networks have been employed to learn the entire analytical model, i.e., its structure and coefficients, using regularized gradient-based optimization. Although this approach tunes the model’s coefficients better, it is prone to premature convergence to suboptimal model structures. Here, we propose a neuro-evolutionary symbolic regression method that combines the strengths of evolutionary-based search for optimal neural network (NN) topologies with gradient-based tuning of the network’s parameters. Due to the inherent high computational demand of evolutionary algorithms, it is not feasible to learn the parameters of every candidate NN topology to the full convergence. Thus, our method employs a memory-based strategy and population perturbations to enhance exploitation and reduce the risk of being trapped in suboptimal NNs. In this way, each NN topology can be trained using only a short sequence of backpropagation iterations. The proposed method was experimentally evaluated on three real-world test problems and has been shown to outperform other NN-based approaches regarding the quality of the models obtained.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/EH22_008%2F0004590" target="_blank" >EH22_008/0004590: Robotika a pokročilá průmyslová výroba</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

GECCO '25: Proceedings of the Genetic and Evolutionary Computation Conference

ISBN

979-8-4007-1465-8

ISSN

—

e-ISSN

—

Počet stran výsledku

9

Strana od-do

1264-1272

Název nakladatele

The ACM Digital Library

Místo vydání

—

Místo konání akce

Malaga

Datum konání akce

14. 7. 2025

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001556459900142