Full-text resources of CEJSH and other databases are now available in the new Library of Science.
Visit https://bibliotekanauki.pl

Results found: 5

first rewind previous Page / 1 next fast forward last

Search results

Search:
in the keywords:  NEURAL NETWORKS
help Sort By:

help Limit search:
first rewind previous Page / 1 next fast forward last
1

ŠTRUKTURÁLNE ZÁVISLOSTI NÁRODNÝCH INOVAČNÝCH SYSTÉMOV: MODELOVANIE NELINEÁRNEJ DYNAMIKY INŠTITÚCIÍ POMOCOU NEURONOVÝCH SIETÍ

100%
Baláž V.
Ekonomický časopis (Journal of Economics)
|
2011
|
vol. 59
|
issue 1
3 – 28
EN
This paper examines structural dependencies within the national innovation systems of 125 countries in period 2006 – 2008. Some 37 partial indicators from the World Economic Forum and World Bank databases are aggregated into 11 independent and 2 dependent variables. Variable relations account for distinctive non-linear dynamics and are modelled via two-step cluster analysis and artificial neural networks. Overall quality of education system, property rights, law and ethics, and competition forces are identified by major predictors for innovativeness. The paper also examines some assumptions by the varieties of capitalism theory on institution complementarities and level of innovativeness. No evidence is found for liberal (coordinated) economies having more efficient innovation systems than mixed ones.
2

STROJOVÉ UČENÍ A MODELOVÁNÍ MĚNOVÝCH KURZŮ V PRAXI FINANČNÍHO ŘÍZENÍ

100%
Buryan P., Taušer J.
Ekonomický časopis (Journal of Economics)
|
2008
|
vol. 56
|
issue 8
781-799
EN
Exchange rates forecasting is an important financial problem that is receiving increasing attention especially because of its difficulty and practical applications. This paper proposes utilisation of Machine Learning methods in the field of financial praxis. Two modelling approaches - enhanced Group Method of Data Handling (GMDH) and back propagation Neural network - were employed for CZK/EUR exchange rate forecasting. Predictions were used for financial management decision simulation of a virtual company and the results indicate, that machine learning proved to be useful source of information in the area. This implies that the proposed modelling approaches can be used as a feasible solution for exchange rate forecasting in exchange rate management.
3

MULTILAYER PERCEPTRONS AS APPROXIMATIONS TO PROBABILITY DENSITY FUNCTIONS IN TIME SERIES FORECASTING

100%
Morajda J.
Przegląd Statystyczny
|
2007
|
vol. 54
|
issue 1
20-33
EN
The paper presents the method of utilisation of multilayer perceptron neural networks to probability densiity function approximation in the problem of time series forecasting. The theoretical background has been given and the specification of neural prediction model, which generates the probability distribution of the forecasted variable in the issue of financial time series predicition, has been described. Next, the research concerning the performance of such model designed for the forecasting of the Polish stock index WIG has been discussed. Two versions of the model have been applied: first - comprised of 12 perceptron networks with single output each, second - based on one network with 12 outputs. Three test cases (for subsequent stock exchange sessions ) have been analysed. Obtained probability distributions are somewhat similar to empirical distribution (achieved for model development data), but they clearly indicate predicted tendency of index change and show specific uncertainty of the forecast.
4
Content available remote

RECEPTION OF LITERATURE GENERATED BY ARTIFICIAL NEURAL NETWORKS

88%
Husárová Z., Piorecký Karel K.
World Literature Studies
|
2022
|
vol. 14
|
issue 1
44 - 60
EN
This article introduces the phenomenon of literature generated by artificial neural networks, with specific examples of texts created in the Czech and Slovak cultural environment. It follows the historical background connected with generative and combinatory poetics and later describes the principles of data processing used by neural networks work; it also presents the parameters of their machine learning. The focus lies on the reception of these artificial texts in the media and in literary studies, leading to the proposition of two reading types specialized for these works: “reading of artificiality” and “literary meta-reading”, while rehabilitating Mathauser’s term of “meta-hability”. The study concludes by suggesting “literary meta-reading of artificiality” as a term that would combine the aforementioned approaches into a new reception of neural network literature.
5

VYUŽITIE SOFTBOTOV NA KULTIVÁCIU EKONOMICKÝCH VEDOMOSTÍ

63%
Andrášik L.
Ekonomický časopis (Journal of Economics)
|
2014
|
vol. 62
|
issue 8
861 – 881
EN
The complex phenomena in a global knowledge-based society and economy are causing difficulties in understanding by conventional modes. The economists should consequently analyse new phenomena. They need to build new theories and disseminating them to wide community. New results in cognitive sciences and progressing ICT, advances in applied informatics and computational intelligence there are arising new opportunities for a dialogue with mental models and theories in the economic sciences. In economics the creation of virtual laboratories and of simulation experimentation with them is useful, for the author uses name “Economic Softbot”. He refers to the dialogue with such softbots as storytelling. The topic of the essay belongs to the class of emergent research/education/learning technologies. Their innovative power is in the dominance of constructive upon instructive approaches and based on holistic qualitative perception of the various complexities.
first rewind previous Page / 1 next fast forward last
JavaScript is turned off in your web browser. Turn it on to take full advantage of this site, then refresh the page.