Topology Optimization of Neural Networks as an Integrated Process in Training with Control Theory Methods

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25530%2F25%3A39923078" target="_blank" >RIV/00216275:25530/25:39923078 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/11047318" target="_blank" >https://ieeexplore.ieee.org/document/11047318</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/PC65047.2025.11047318" target="_blank" >10.1109/PC65047.2025.11047318</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Topology Optimization of Neural Networks as an Integrated Process in Training with Control Theory Methods

Popis výsledku v původním jazyce

The simultaneous optimization of neural network topology and training remains an underexplored research direction, despite its potential to improve model efficiency and performance dynamically. This paper introduces a control-based framework for jointly adjusting the structure and training process of fully connected neural networks. The methodology formulates the training and pruning process as a multivariable dynamic system with two input variables-training process parameters and network architecture adjustments-and two output variables-model performance and computational complexity. A discrete two-dimensional Proportional-Integral-Derivative (PID) controller is employed to regulate these inputs, ensuring a balanced trade-off between accuracy and computational efficiency. The control system is tested on a function approximation task, where a fully connected network is initially set with redundant capacity and gradually optimized according to predefined reference trajectories of performance and complexity. Experimental results demonstrate the effectiveness of the proposed approach, revealing the dynamic interaction between topology and training in realtime network adaptation. The findings highlight the feasibility of integrating control strategies into neural network optimization and pave the way for future research on more advanced control-based learning architectures.

Název v anglickém jazyce

Topology Optimization of Neural Networks as an Integrated Process in Training with Control Theory Methods

Popis výsledku anglicky

The simultaneous optimization of neural network topology and training remains an underexplored research direction, despite its potential to improve model efficiency and performance dynamically. This paper introduces a control-based framework for jointly adjusting the structure and training process of fully connected neural networks. The methodology formulates the training and pruning process as a multivariable dynamic system with two input variables-training process parameters and network architecture adjustments-and two output variables-model performance and computational complexity. A discrete two-dimensional Proportional-Integral-Derivative (PID) controller is employed to regulate these inputs, ensuring a balanced trade-off between accuracy and computational efficiency. The control system is tested on a function approximation task, where a fully connected network is initially set with redundant capacity and gradually optimized according to predefined reference trajectories of performance and complexity. Experimental results demonstrate the effectiveness of the proposed approach, revealing the dynamic interaction between topology and training in realtime network adaptation. The findings highlight the feasibility of integrating control strategies into neural network optimization and pave the way for future research on more advanced control-based learning architectures.

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/EH23_021%2F0008402" target="_blank" >EH23_021/0008402: Mezisektorová a mezioborová spolupráce ve výzkumu a vývoji komunikačních, informačních a detekčních technologií pro řídicí a zabezpečovací systémy</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

2025 25TH INTERNATIONAL CONFERENCE ON PROCESS CONTROL, PC

ISBN

—

ISSN

2995-1720

e-ISSN

2995-1739

Počet stran výsledku

8

Strana od-do

—

Název nakladatele

IEEE

Místo vydání

NEW YORK

Místo konání akce

Strbske Pleso

Datum konání akce

3. 6. 2025

Typ akce podle státní příslušnosti

EUR - Evropská akce

Kód UT WoS článku

001541574400007