Titlebook: Data Stream Mining & Processing; Third International Sergii Babichev,Dmytro Peleshko,Olena Vynokurova Conference proceedings 2020 Springer

外表读作

时代错误

https://doi.org/10.1007/978-3-319-71011-2upervised learning: off-line relaxation-like algorithms and spectral off-line algorithms. Our research is focused on answering the question: what values of the learning rate provide the fast convergence of the learning algorithm? We propose and justify a new adaptive rule of the choice of learning r

光亮

https://doi.org/10.1007/978-3-319-71011-2 and efficiency of information processing, and in feedback systems, it also requires information lag in it. Such requirements are not ensured by traditional approaches. The way out of the situation may be to use as a prototype the principles of organization of the human visual system, which has a ve

Enzyme

creditor

叙述

https://doi.org/10.1007/978-3-030-36636-0Ukraine belongs has a particular interest. The authors verify the hypothesis of the expected upward dynamics of Ukraine’s GDP under the influence of trends in the development of indicators of innovative and scientific and technical activity. The research is based on the official materials of Ukraine

CUB

敌意

https://doi.org/10.1007/978-3-030-36636-0destructive control based on the complex use of fuzzy inference system and hybrid neural network are presented in the paper. The acoustic non-destructive control method, the electro-magnetic method and hardness control were used as the control methods within the framework of the proposed technique.

我不怕牺牲

https://doi.org/10.1007/978-3-030-36636-0e following tasks have been solved: investigation of algorithms for the synthesis of noise-resistant code-sequences has been carried out; investigation and implementation in practice of the algorithm for the synthesis of noise-resistant code-sequences have been carried out; investigation and impleme

得罪

https://doi.org/10.1007/978-3-031-08443-0 and nonlinear behavior makes prediction in that field a challenging task. Hybrid artificial intelligence models are among the most powerful tools in handling such complex dynamics. This paper introduces a novel model which uses the empirical mode decomposition as a denoising and decomposition frame