scholarly journals Advanced Temporal-Difference Learning for Intrusion Detection∗∗This work was supported by the Russian Foundation for Basic Research (Grants No. 13-07-00183 A, 13-08-12151 ofi_m_RZHD, 13-07-00226 A, 14-01-00259 A and 13-07-13109 ofi_m_RZHD) and partially supported by Grant of SGS No. SP2015/151, VŠB - Technical University of Ostrava, Czech Republic

2015 ◽  
Vol 48 (4) ◽  
pp. 43-48 ◽  
Author(s):  
Sukhanov A.V. ◽  
Kovalev S.M. ◽  
Stýskala V.
2001 ◽  
Vol 13 (10) ◽  
pp. 2221-2237 ◽  
Author(s):  
Rajesh P. N. Rao ◽  
Terrence J. Sejnowski

A spike-timing-dependent Hebbian mechanism governs the plasticity of recurrent excitatory synapses in the neocortex: synapses that are activated a few milliseconds before a postsynaptic spike are potentiated, while those that are activated a few milliseconds after are depressed. We show that such a mechanism can implement a form of temporal difference learning for prediction of input sequences. Using a biophysical model of a cortical neuron, we show that a temporal difference rule used in conjunction with dendritic backpropagating action potentials reproduces the temporally asymmetric window of Hebbian plasticity observed physiologically. Furthermore, the size and shape of the window vary with the distance of the synapse from the soma. Using a simple example, we show how a spike-timing-based temporal difference learning rule can allow a network of neocortical neurons to predict an input a few milliseconds before the input's expected arrival.


Author(s):  
Martin Kropik ◽  
Jiri Duspiva

The contribution provides information about the development of a system for visualization of NPP severe accident progress. This visualization is under development in cooperation of UJV Rez, a.s. and Czech Technical University in Prague. The project is supported by the Technology Agency of the Czech Republic and is planned to be solved from 2015 to 2017. The visualization uses results of an analytical code MELCOR for evaluation of the NPP severe accident progress. The visualization firstly reads MELCOR results, transforms them to a suitable format for quick processing and provides graphical screens with reactor components that could demonstrate the progress of the evaluated severe accident. The visualization can even provide parallel presentation of more different scenarios of the severe accident. The system is planned to be used for training of NPP staff to handle severe accidents. In the first year of the project solution (2015), the software for MELCOR data transformation, next for providing information about transformed data were developed. In the following year (2016), software for creation of graphical screens with reactor components and software for severe accident progress presentation is creating. In the final year of the project (2017), thorough testing is going to be carried out, and the applicability of the visualization for a practical use during a NPP staff training is going to be verified.


2021 ◽  
Vol 900 (1) ◽  
pp. 011001

3rd International Conference “Advances in Environmental Engineering” (AEE 2021) organised by Faculty of Mining and Geology of the VŠB-Technical University of Ostrava, Czech Republic and Faculty of Civil Engineering of the Technical University of Košice, Slovak republic, was held in November 25-26, 2021 online. This year the conference offered an virtual platform for the dissemination of original research results, new ideas and discovered advances in the field of environmental engineering and related interdisciplinary topics. List of Preface, Sponsors, Editors, Scientific Committee, Organising Guarantees, Review Statement, List Of Reviewers are available in this pdf.


Sign in / Sign up

Export Citation Format

Share Document