<script type="text/javascript">
<!--
document.write('<div id="oa_widget"></div>');
document.write('<script type="text/javascript" src="https://www.openaire.eu/index.php?option=com_openaire&view=widget&format=raw&projectId=undefined&type=result"></script>');
-->
</script>
Ð”Ð°Ð½Ð½Ð°Ñ Ñ€Ð°Ð±Ð¾Ñ‚Ð° поÑвÑщена нахождению оптимальных гиперпараметров Ð´Ð»Ñ Ð¼Ð¾Ð´ÐµÐ»ÐµÐ¹ машинного Ð¾Ð±ÑƒÑ‡ÐµÐ½Ð¸Ñ Ð´Ð¾Ð±Ñ‹Ð²Ð°ÑŽÑ‰Ð¸Ñ… Ñкважин. Ð’ рамках иÑÑÐ»ÐµÐ´Ð¾Ð²Ð°Ð½Ð¸Ñ Ñ€Ð°ÑÑматривалиÑÑŒ 4 метода оптимизации гиперпараметров моделей: Grid Search, Random Search, CmaEsSampler (CMA-ES) из библиотеки Optuna и Tree-structured Parzen Estimator (TPE) из библиотеки Hyperopt. Был проведен анализ данных Ñ Ð¼ÐµÑторождений, и поÑтроены доверительные интервалы значений гиперпараметров Ð´Ð»Ñ ÐºÐ°Ð¶Ð´Ð¾Ð¹ из предÑтавленных моделей. Результаты предÑтавлены в виде графиков и таблиц, Ñравнивающих точноÑть предÑказанных значений целевой переменной и времÑ, затраченное на работу каждого из методов.Â
This work is devoted to finding optimal hyperparameters for machine learning models of producing wells. The study considered 4 methods for optimizing hyperparameters of models: Grid Search, Random Search, CmaEsSampler (CMA-ES) from the Optuna library and Tree-structured Parzen Estimator (TPE) from the Hyperopt library. The analysis of data from the deposits was carried out, and confidence intervals of hyperparameter values for each of the presented models were constructed. The results are presented in the form of graphs and tables comparing the accuracy of the predicted values of the target variable and the time spent on the operation of each of the methods.
гипеÑпаÑамеÑÑÑ, machine learning, довеÑиÑелÑнÑе инÑеÑвалÑ, меÑÐ¾Ð´Ñ Ð¾Ð¿ÑимизаÑии, маÑинное обÑÑение, optimization methods, hyperparameters, confidence intervals, Python
гипеÑпаÑамеÑÑÑ, machine learning, довеÑиÑелÑнÑе инÑеÑвалÑ, меÑÐ¾Ð´Ñ Ð¾Ð¿ÑимизаÑии, маÑинное обÑÑение, optimization methods, hyperparameters, confidence intervals, Python
citations This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |