Висторобська, Лоліта Вячеславівна2023-06-292023-06-292022Висторобська, Л. В. Аналіз ефективності алгоритмів випадкового пошуку в машинному навчанні : дипломна робота магістра / Л. В. Висторобська. – Одеса, 2022. – 62 с.https://dspace.onu.edu.ua/handle/123456789/35594Optimization is a frequent goal in many studies, and here optimization in the context of neural networks will be discussed as well, namely the optimization of hyper parameters. Here, a set of methods is to be evaluated and compared with significant emphasis on random search and natural computing algorithms. So let us introduce the first base term referring to this work, namely as from [1] Stochastic optimization (SO) methods are optimization methods that generate and use random variables. For stochastic problems, the random variables appear in the formulation of the optimization problem itself, which involves random objective functions or random constraints. Stochastic optimization methods also include methods with random iterates. More specific sub-type of such methods introduced here are Natural Computing (NC) ones.en113 прикладна математикаосвітня програма прикладна математикаalgorithmsефективністьmachine learningrandom searchDiplomas