1. Главная
  2. Ресурсы
  3. Библиотечный поиск
Evolutionary searchalgorithm forlearning activationfunction of anartificial neuralnetwork Yurshin Viacheslav2025 год

Evolutionary search algorithm for learning activation function of an artificial neural network : доклад, тезисы доклада
доклад, тезисы доклада, статья из сборника материалов конференций

Дополнительные ссылки: eLibrary · Источник статьи
База данных: Каталог библиотеки СФУ
Библиографическое описание: Evolutionary search algorithm for learning activation function of an artificial neural network : доклад, тезисы доклада / V. V. Yurshin. - [S. l. : s. n.], 2025. - Текст : непосредственный // ITM Web of Conferences : III International Workshop / Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-III 2024) (2024 ; 02.12 - 04.12 ; Krasnoyarsk). - Krasnoyarsk, 2025. - P. 5004. - This work was supported by the Ministry of Science and Higher Education of the Russian Federation (grant No. 075-15-2022-1121). - DOI 10.1051/itmconf/20257205004.
Аннотация: Neural networks require careful selection of activation functions to optimize performance. Traditional methods of choosing activation functions through trial and error are time-consuming and resource-intensive. This paper presents a novel approach to automatically design activation functions for artificial neural networks using genetic programming combined with gradient descent. The proposed method aims to enhance the efficiency of the search process for optimal activation functions. Our algorithm employs genetic programming to evolve the general form of activation functions, while gradient descent optimizes their parameters during network training. This hybrid approach allows for the exploration of a wide range of potential activation functions tailored to specific tasks and network architectures. The method was evaluated on three datasets from the KEEL repository: Iris, Titanic, and Phoneme. The results demonstrate the algorithm's ability to generate and optimize custom activation functions, although improvements in network accuracy were not observed in this initial study. This work contributes to the ongoing research in neural network optimization and opens avenues for further investigation into the automatic design of activation functions.
Год издания: 2025
Авторы: Yurshin Viacheslav
Издательство: Krasnoyarsk
Источник: ITM Web of Conferences
Номера страниц: 5004
Держатель оригинала документа: Siberian Federal University, Institute of Space and Information Technologies
Мероприятие: Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-III 2024) (Krasnoyarsk, 2024 ; 02.12 - 04.12)
Количество экземпляров:
Твёрдая копия издания отсутствует в фонде библиотеки

Похожие публикации

Multi-objectiveparametric synthesisof loss functions inneural networks withevolutionaryalgorithms Morozov EduardStanovov Vladimir2024 год

Multi-objective parametric synthesis of loss functions in neural networks with evolutionary… : доклад, тезисы доклада

  • Morozov Eduard и др.
  • 2024 год
Artificial NeuralNetwork ArchitectureTuning Algorithm Yurshin V. G.Stanovov V. V.2022 год

Artificial Neural Network Architecture Tuning Algorithm : доклад, тезисы доклада

  • Yurshin V. G. и др.
  • 2022 год
Neural network-basedvehicle control insimulatedenvironments usingreal-coded geneticalgorithms Shabalin DenisStanovov Vladimir2025 год

Neural network-based vehicle control in simulated environments using real-coded genetic… : доклад, тезисы доклада

  • Shabalin Denis и др.
  • 2025 год
The method of optimalresource managementof a distributeddynamic system basedon the algorithm ofzeroing neural… Bryukhanova Evgenia2024 год

The method of optimal resource management of a distributed dynamic system based on the… : доклад, тезисы доклада

  • Bryukhanova Evgenia
  • 2024 год
Optimizing neuralnetwork loss functionwith differentialevolution Morozov EduardStanovov VladimirGorbunov Sergey2026 год

Optimizing neural network loss function with differential evolution : доклад, тезисы доклада

  • Morozov Eduard и др.
  • 2026 год
Self-ConfiguringEvolutionaryAlgorithms BasedDesign of HybridInterpretable MachineLearning Models Sherstnev P. A.2022 год

Self-Configuring Evolutionary Algorithms Based Design of Hybrid Interpretable Machine… : доклад, тезисы доклада

  • Sherstnev P. A.
  • 2022 год
Software developmentbased on artificialneural networks forfitness club Tynchenko V.S.Bukhtoyarov V.V.Bocharov A.N.2022 год

Software development based on artificial neural networks for fitness club : доклад, тезисы доклада, статья из…

  • Tynchenko V.S. и др.
  • 2022 год
Software developmentbased on artificialneural networks forfitness club Tynchenko Vadim S.Bukhtoyarov Vladimir V.Bocharov Aleksey N.2022 год

Software development based on artificial neural networks for fitness club : доклад, тезисы доклада

  • Tynchenko Vadim S. и др.
  • 2022 год

Показать ещё

AUTOMATIC GENERATIONOF NEURAL NETWORKARCHITECTURES BYMULTI-OBJECTIVEGENETIC ALGORITHM Edreev VladimirStanovov Vladimir2025 год

AUTOMATIC GENERATION OF NEURAL NETWORK ARCHITECTURES BY MULTI-OBJECTIVE GENETIC ALGORITHM : научное издание

  • Edreev Vladimir и др.
  • 2025 год
Software forStructure Selectionof an ArtificialNeural Network toControl the InductionSoldering Process Milov A.Tynchenko V.Bukhtoyarov V.2020 год

Software for Structure Selection of an Artificial Neural Network to Control the Induction Soldering Process : доклад,…

  • Milov A. и др.
  • 2020 год
Multi-CriteriaGenetic Algorithm forOptimizingDistributed ComputingSystems in NeuralNetwork Synthesis Tynchenko Valeriya V.Malashin IvanKurashkin Sergei O.2025 год

Multi-Criteria Genetic Algorithm for Optimizing Distributed Computing Systems in Neural Network… : научное издание

  • Tynchenko Valeriya V. и др.
  • 2025 год
Soil PropertiesClassification inSustainableAgriculture UsingGeneticAlgorithm-Optimizedand Deep NeuralNetworks Tynchenko YadvigaTynchenko VadimKukartsev Vladislav2024 год

Soil Properties Classification in Sustainable Agriculture Using Genetic Algorithm-Optimized and… : научное издание

  • Tynchenko Yadviga и др.
  • 2024 год
Evolutionaryalgorithms for thedesign of neuralnetwork classifiersfor theclassification ofpain intensity Mamontov D.Polonskaia I.Skorokhod A.2019 год

Evolutionary algorithms for the design of neural network classifiers for the classification of pain… : научное издание

  • Mamontov D. и др.
  • 2019 год
Digital processing ofsatellite imagesusing neural networkalgorithms Kochanov AndreyZolotukhin VyacheslavMironenko Vladislav2022 год

Digital processing of satellite images using neural network algorithms : доклад, тезисы доклада

  • Kochanov Andrey и др.
  • 2022 год
Exploring the Impactof Pre-MechanicalActivation of NickelPowder on theStructure ofDeposited Metal: ADeep Neural… Malashin IvanKobernik NikolayPankratov Alexandr2024 год

Exploring the Impact of Pre-Mechanical Activation of Nickel Powder on the Structure of Deposited… : статья из журнала

  • Malashin Ivan и др.
  • 2024 год

Hands-On Deep Learning for IoT. Train Neural Network Models to Develop Intelligent IoT Applications : научное издание

  • Razzaque Mohammad Abdur и др.
  • 2019 год