Machine learning (ML) relies on stochastic algorithms, all of which rely gradient approximations with \textquotedbl{}batch size\textquotedbl{} examples. Growing the batch size as optimization proceeds is a simple and usable method to reduce training time, provided that number workers grows size. In this work, we provide package trains PyTorch models Dask clusters, can grow if desired. Our simul...

Predicting rainfall is an important step in generating data for climate impact studies. Rainfall predictions are a key process providing assessments with inputs. A consistent pattern typically good normal plants; nevertheless, too much or little can be disastrous to crops, even deadly. Drought damage plants and lead erosion, while heavy encourage the growth of destructive fungi. Machine Learnin...

Here, we study machine learning (ML) architectures to solve a mean-field games (MFGs) system arising in price formation models. We formulate training process that relies on min–max characterization of the optimal control and variables. Our main theoretical contribution is development posteriori estimates as tool evaluate convergence process. illustrate our results with numerical experiments for...

Machine learning (ML) models have been quite successful in predicting outcomes many applications. However, some cases, domain experts might a judgment about the expected outcome that conflict with prediction of ML models. One main reason for this is training data not be totally representative population. In paper, we present novel framework aims at leveraging experts' to mitigate conflict. The ...

The evaluation of machine learning models is a crucial step before their application because it is essential to assess how well a model will behave for every single case. In many real applications, not only is it important to know the “total” or the “average” error of the model, it is also important to know how this error is distributed and how well confidence or probability estimations are mad...

In this thesis we present approaches to the creation and usage of semantic models by the analysis of the data spread in the feature space. We aim to introduce the general notion of using feature selection techniques in machine learning applications. The applied approaches obtain new feature directions on data, such that machine learning applications would show an increase in performance. We rev...

Data of different levels of complexity and of ever growing diversity of characteristics are the raw materials that machine learning practitioners try to model using their wide palette of methods and tools. The obtained models are meant to be a synthetic representation of the available, observed data that captures some of their intrinsic regularities or patterns. Therefore, the use of machine le...

In the quest for alternatives to traditional complementary metal-oxide-semiconductor, it is being suggested that digital computing efficiency and power can be improved by matching the precision to the application. Many applications do not need the high precision that is being used today. In particular, large gains in area and power efficiency could be achieved by dedicated analog realizations o...