|
|
Computational modelling of thermal behavior of DC motor
Grepl, Robert ; Wierciak, J. ; Vlach, R.
The paper deals with computational modelling of thermal behavior ofdrive system with DC motor. Motivation to built dynamical thermal model is toincrease utility value performance of electrical motor in particular roboticapplication. There is mathematical model presented in the paper, describedidentification of parameters process and shown results for two kind ofidentification approaches. Usage of neural networks approximators ismentioned.
|
|
|
Floods Prediction Possibility by Means of Neural Networks
Neruda, M. ; Neruda, Roman
The article deals with studying rainfall-runoff relations on the Plouťnice catchment. With help of a method Artificial neural network we established few models of rainfall-runoff dependence in past days. The neural model then can predict runoff values onthe base of historical data. Calculated runoff can help with prediction of flooding on rivers.
|
|
|
O nemožnosti učení neuronů s impulsy
Sgall, Jiří ; Šíma, J.
The computational complexity of training a single spiking neuron N with adjustable synaptic delays and binary coded inputs and output is studied. A synchronization technique is introduced so that the results concerning the non-learnability of spiking neurons with binary delays are generalized to arbitrary delays.
|
|
| |
|
| |
|
|
Use of Neural Networks in Equity Trading
Lahodová, Martina ; Veselá, Jitka (advisor) ; Stádník, Bohumil (referee)
The neural networks have been the fastest developing area of computer science lately. They have strong interdisciplinary character, so that they can be applied in many fields of human activity e.g. capital markets. The objective of the thesis is to apply a perceptron model to predicting future value of a sample of shares, to set the accuracy of prediction and bring the conclusion of reliable use of the neural networks. Opening chapters are concerned with general principles of neural networks functioning, their classification and different ways of their "learning". Analytic chapter is based on the creation and use of the perceptron model and the analysis of given results.
|
|
|
Applications of neural networks and Elliot´s waves on selected shares
Polaková, Soňa ; Veselá, Jitka (advisor) ; Musílek, Petr (referee)
Using modern methods of share quotations forecasting is the main goal of this thesis. The special accent is placed on forecasting the trend by means of artificial neural network especially on the optimalization of variables in the training process. Elliot's wave theory is applied in the second part of the thesis, particularly on prediction of future share quotation progress. Buying or selling signal generated by these two methods is consequently compared with ex-post signal yielding a profit. Lastly, successfulness of using these methods for forecasting at stock market is evaluated.
|
|
|
Analysis of Stock Exchange Data to UI Methods
Kutina, Michal ; Jelínek, Jiří (advisor) ; Dvořák, Pavel (referee)
The graduation thesis "Analysis of stock-exchange data using AI methods" is focused on the use of neural networks while predicating the exchange-rate movements on Change. The theoretical part is divided into three independent units. The Change matters and the related individual terms are described in the first part. In the second part, the two basic approaches to the stock-exchange data analysis are analyzed, these two approaches being the fundamental and technical analysis. The third, and the last, theoretical part forms an individual unit describing the Artificial Intelligence theory. Particularly the issue of the neuronal networks is described in detail. The practical part seeks the use for the chosen neuronal network GAME. It analyses the chosen YMZ9 market. It focuses on the prediction of the exchange-rate movements using the "sliding window" method. The last chapter summarizes the results and it proves that under certain circumstances it is possible to properly use the neuronal networks both for the prediction of the stock-exchange movements and as one of the corner-stones of the profitable trading system.
|
|
|
History of Artificial Intelligence - Neural Networks
Šuchman, Ondřej ; Jirků, Petr (advisor) ; Berka, Petr (referee)
The main aim of my bachelor thesis is to map historical development of neural networks from the beginning (first mathematical model of neuron from 1943) to present and application of neural networks to "intelligent" devices, which can recognize the patterns, graphical data or convert English written text to the oral form (NETtalk). I have carefully studied the literature named in the chapter "Literatura a zdroje" in order to achieve this aim. In the first charter there is the theoretical survey about the field of artificial intelligence and neural networks. Then the thesis is well-arranged to five periods, which were important for neural networks in either good or bad way. To the most important discoveries are dedicated more space and there is mentioned their functionality and using possibilities. There is not enough space on this thesis to cover all the neural networks ever made. The aim of the thesis is to demostrate certain kinds of networks, their first usage, the most important algorithms and also to mention the significant applications of neural networks.
|
|
|
Modern Methods for Exchange Rete Prediction
Buryan, Petr ; Taušer, Josef (advisor)
Tato práce se snaží nabídnout odpověď na otázku, zda má smysl při rozhodování o budoucím pohybu měnových kurzů brát ohled na výsledky vystupující z modelů získaných analýzou měnových kurzů a relevantních časových řad provedeného pomocí metod strojového učení. Účelem této práce je tak prozkoumat možnosti analýzy kurzů (ve formě časových řad) s důrazem na použití nových metod spočívajících svým těžištěm v oblasti umělé inteligence a strojového učení (neuronové sítě, algoritmus GMDH sítí).
|
guest ::
