An analytical approach for unsupervised learning rate estimation using rectified linear units.

Unsupervised learning based on restricted Boltzmann machine or autoencoders has become an important research domain in the area of neural networks. In this paper mathematical expressions to adaptive learning step calculation for RBM with ReLU transfer function are proposed. As a result, we can automatically estimate the step size that minimizes the loss function of the neural network and correspondingly update the learning step in every iteration.

Sports activity and changes in physical fitness of Polish children and adolescents: OSF study.

Background: Physical activity promotion programs for children and adolescents should constitute the basis of any national health policy aiming to improve physical fitness, which is a significant health indicator in children, adolescents, adults as well as elderly persons.

Methods: The study included 1,230 children and adolescents aged 8-16 years (60.1% of girls) from Poland.

Assessment of Motor Abilities and Physical Fitness in Youth in the Context of Talent Identification-OSF Test.

(1) Background: Physical fitness during childhood is an important indicator of current and future health status. Defining physical fitness levels is a key element of talent identification in the training of children and adolescents. It is also crucial in developing a sports career path.