Towards Transparent, Physically Consistent Machine Learning Models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21730%2F25%3A00385833" target="_blank" >RIV/68407700:21730/25:00385833 - isvavai.cz</a>

Výsledek na webu

<a href="https://icinco.scitevents.org/KeynoteSpeakers.aspx" target="_blank" >https://icinco.scitevents.org/KeynoteSpeakers.aspx</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Towards Transparent, Physically Consistent Machine Learning Models

Popis výsledku v původním jazyce

As machine learning is being rapidly adopted in a wide range of domains, the need for models that are both accurate and physically interpretable has never been more critical. This talk explores recent advances in symbolic regression, a rapidly evolving field that aims to derive concise, human-understandable models from data. The goal is to provide researchers and practitioners with actionable insights into building next-generation equation learners that combine the rigor of physics with the power of machine learning, even when training on sparse datasets. We begin by examining the evolution from traditional genetic programming (GP)-based symbolic regression to neural architectures that incorporate prior system knowledge and enforce physical plausibility. We then expand this paradigm to neuro-evolutionary algorithms that combine evolutionary search for neural network topologies with gradient-based fine-tuning of their parameters. Finally, we discuss transformer-based architectures that reduce the computational burden by pre-training a large, generic model that can be quickly queried for unseen data during the inference step. We give application examples from robotics where these advances are particularly impactful in providing accurate yet interpretable dynamic models, which are essential for reliable control, planning, and optimization.

Název v anglickém jazyce

Towards Transparent, Physically Consistent Machine Learning Models

Popis výsledku anglicky

As machine learning is being rapidly adopted in a wide range of domains, the need for models that are both accurate and physically interpretable has never been more critical. This talk explores recent advances in symbolic regression, a rapidly evolving field that aims to derive concise, human-understandable models from data. The goal is to provide researchers and practitioners with actionable insights into building next-generation equation learners that combine the rigor of physics with the power of machine learning, even when training on sparse datasets. We begin by examining the evolution from traditional genetic programming (GP)-based symbolic regression to neural architectures that incorporate prior system knowledge and enforce physical plausibility. We then expand this paradigm to neuro-evolutionary algorithms that combine evolutionary search for neural network topologies with gradient-based fine-tuning of their parameters. Finally, we discuss transformer-based architectures that reduce the computational burden by pre-training a large, generic model that can be quickly queried for unseen data during the inference step. We give application examples from robotics where these advances are particularly impactful in providing accurate yet interpretable dynamic models, which are essential for reliable control, planning, and optimization.

Druh

O - Ostatní výsledky

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