Piotr Duda, Maciej Jaworski, Andrzej Cader and Lipo Wang
In recent years, many deep learning methods, allowed for a significant improvement of systems based on artificial intelligence methods. Their effectiveness results from an ability to analyze large labeled datasets. The price for such high accuracy is the long training time, necessary to process such large amounts of data. On the other hand, along with the increase in the number of collected data, the field of data stream analysis was developed. It enables to process data immediately, with no need to store them. In this work, we decided to take advantage of the benefits of data streaming in order to accelerate the training of deep neural networks. The work includes an analysis of two approaches to network learning, presented on the background of traditional stochastic and batch-based methods.
Tadeusz Groń, Magdalena Piątkowska, Elżbieta Tomaszewicz, Bogdan Sawicki, Piotr Urbanowicz and Henryk Duda
Polycrystalline samples of new scheelite-type tungstates, Pb1−3x xPr2xWO4 with 0.0098 ⩽ x ⩽ 0.20, where denotes cationic vacancies have been successfully prepared by a high-temperature solid-state reaction method using Pr2(WO4)3 and PbWO4 as the starting reactants. The influence of the Pr3+ substitution in the scheelite framework on the structure and optical properties of prepared new ceramic materials has been examined using powder X-ray diffraction method (XRD) and UV-Vis-NIR spectroscopy. The results of dielectric studies of Pb1−3x xPr2xWO4 samples showed both low values of dielectric constant (below 14) and loss tangent (below 0.2). The electrical conductivity and thermoelectric power measurements revealed a low conductivity (∼2 × 10−9 S/m) and the sign change of thermoelectric power around the temperature of 366 K suggesting the p-n transition. These results are discussed in the context of vacancy, acceptor and donor levels as well as the Maxwell-Wagner model.