1. Главная
  2. Ресурсы
  3. Библиотечный поиск
×

Сообщение об ошибке

Электронный каталог библиотеки временно недоступен, поэтому сведения могут отсутствовать, быть неполными или устаревшими.
Multi-objectiveparametric synthesisof loss functions inneural networks withevolutionaryalgorithms : доклад,тезисы доклада Morozov EduardStanovov Vladimir2024 год

Multi-objective parametric synthesis of loss functions in neural networks with evolutionary algorithms : доклад, тезисы доклада
доклад, тезисы доклада, статья из сборника материалов конференций

База данных: Каталог библиотеки СФУ
Аннотация: The loss function is a fundamental aspect of neural network training and by choosing a suitable one, better results can be achieved. In classification problems, the cross-entropy loss function is almost exclusively used. In this paper the loss function represented by Taylor's series which are optimized with multi-objective evolutionary algorithm. As results show the new loss function can be better than cross-entropy, however application of multi-objective algorithm does not bring an improvement in comparison with single-objective algorithm.
Год издания: 2024
Авторы: Morozov Eduard, Stanovov Vladimir
Источник: Hybrid Methods of Modeling and Optimization in Complex Systems (HMMOCS-II-2023)

Похожие публикации

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

  • Yurshin Viacheslav
  • 2025 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
A comparative studyof state-of-the-artmulti-objectiveoptimizationalgorithms Li JiaweiSopov Evgenii2024 год

A comparative study of state-of-the-art multi-objective optimization algorithms : доклад, тезисы доклада

  • Li Jiawei и др.
  • 2024 год
Application of theevolutionary approachto structural andparametricidentification ofdynamic objects Karaseva Tatiana2024 год

Application of the evolutionary approach to structural and parametric identification of… : доклад, тезисы доклада

  • Karaseva Tatiana
  • 2024 год
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
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
EVOLUTIONARYALGORITHMS FORSOLVINGMULTI-OBJECTIVEOPTIMIZATION PROBLEMS Bezvorotnykh A.V.Shelikhova S.V.2025 год

EVOLUTIONARY ALGORITHMS FOR SOLVING MULTI-OBJECTIVE OPTIMIZATION PROBLEMS : научное издание

  • Bezvorotnykh A.V. и др.
  • 2025 год
On a restartmetaheuristic forreal-valuedmulti-objectiveevolutionaryalgorithms Brester C.Ryzhikov I.Kolehmainen M.2019 год

On a restart metaheuristic for real-valued multi-objective evolutionary algorithms : доклад, тезисы доклада

  • Brester C. и др.
  • 2019 год

Показать ещё

A Multi-ObjectiveOptimization ofNeural Networks forPredicting thePhysical Propertiesof Textile PolymerComposite… Malashin IvanTynchenko VadimGantimurov Andrei2024 год

A Multi-Objective Optimization of Neural Networks for Predicting the Physical Properties of… : статья из журнала

  • Malashin Ivan и др.
  • 2024 год
The multi-objectiveoptimization ofcomplex objectsneural network models Tynchenko V.S.Tynchenko V.V.Bukhtoyarov V.V.2016 год

The multi-objective optimization of complex objects neural network models : статья из журнала

  • Tynchenko V.S. и др.
  • 2016 год
A Hybridization ofLocal and GlobalSearch for DynamicMulti-ObjectiveOptimization Problem Rurich MariaSherstnev Pavel2022 год

A Hybridization of Local and Global Search for Dynamic Multi-Objective Optimization Problem : доклад, тезисы доклада

  • Rurich Maria 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
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
Minimizingunnecessary taxaudits usingmulti-objectivehyperparameter tuningof XGBoost with focalloss Malashin Ivan P.Masich Igor S.Tynchenko Vadim S.2025 год

Minimizing unnecessary tax audits using multi-objective hyperparameter tuning of XGBoost with focal… : научное издание

  • Malashin Ivan P. и др.
  • 2025 год
Multi-objectiveevolutionary approachin the lineardynamical systeminverse modeling Ryzhikov I.Brester C.Kolehmainen M.2018 год

Multi-objective evolutionary approach in the linear dynamical system inverse modeling : доклад, тезисы доклада

  • Ryzhikov I. и др.
  • 2018 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