Institute of Theoretical and Applied Informatics, Polish Academy of Sciences

The topic of the talk concerns an innovative approach in the preparation of data used for training of convolutional neural networks for segmentation of color images. The problem of selecting training data and acquiring enough of them, necessary to obtain a model with the highest possible predictive accuracy, is an important issue in the topic of neural networks. Incorrect approach to it can cause that even the best prepared network architecture will not be able to generate a model that will work with satisfactory accuracy.

Gilbert proposed an iterative algorithm for bounding the distance between a given point and a convex set. We apply the Gilbert's algorithm with a few modifications and simplifications to get an upper bound on the Hilbert-Schmidt distance between a given state and the set of separable states. While Hilbert-Schmidt distance does not form a proper entanglement measure, it can nevertheless be used as a very robust indicator of the amount of entanglement.

Innovation and searching for new solutions is a key element of continuous improvement of railroad undertakings' safety management systems. Therefore, supporting the existing systems with IT solutions gives wide and new possibilities for presentation and analysis of data collected in different areas of railroad companies' operation. Such a situation occurs, among others, in the case of information on events and incidents occurring on the railroad network.