|
|
Deep Neural Networks Used for Customer Support Cases Analysis
Marušic, Marek ; Ryšavý, Ondřej (referee) ; Pluskal, Jan (advisor)
Umelá inteligencia je pozoruhodne populárna v dnešnej dobe, pretože si dokáže poradiť s rôznymi veľmi komplexnými úlohami v odvetviach ako napr. spracovanie obrazu, spracovanie zvuku, spracovanie prirodzeného jazyka a podobne. Keďže Red Hat doteraz už vyriešil obrovksé množstvo zákazníckych požiadavkov počas podpory rôznych produktov. Preto bola navrhnutá myšlienka použiť umelú inteligenciu práve na tieto dáta a docieliť tak zlepšenie a zrýchlenie procesu riešenia zákaznícky požiadavkov. V tejto práci sú popísané použité techniky na spracovanie týchto dát a úlohy, ktoré je možné riešiť pomocou hlbokých neurónových sietí. Taktiež sú v tejto práci popísane rôzne modely, ktoré boli vytvorené počas riešenia tejto práce a snažia sa adresovať rôzne úlohy. Ich výkony sú porovnané na spomínaných úlohách.
|
|
|
Machine Learning Optimization of KPI Prediction
Haris, Daniel ; Burget, Radek (referee) ; Bartík, Vladimír (advisor)
This thesis aims to optimize the machine learning algorithms for predicting KPI metrics for an organization. The organization is predicting whether projects meet planned deadlines of the last phase of development process using machine learning. The work focuses on the analysis of prediction models and sets the goal of selecting new candidate models for the prediction system. We have implemented a system that automatically selects the best feature variables for learning. Trained models were evaluated by several performance metrics and the best candidates were chosen for the prediction. Candidate models achieved higher accuracy, which means, that the prediction system provides more reliable responses. We suggested other improvements that could increase the accuracy of the forecast.
|
|
|
Sleep scoring using artificial neural networks
Vašíčková, Zuzana ; Mézl, Martin (referee) ; Králík, Martin (advisor)
Hlavným cieľom semestrálnej práce je vytvorenie umelej neurónovej siete, ktorá bude schopná roztriediť spánok do spánkových epoch. Na začiatku je uvedené zhrnutie informácií o spánku a spánkových epochách. V ďalších kapitolách sa nachádza dôkladnejší prehľad metod na spracovávanie signálov a na klasifikáciu. Po zhrnutí teoretických znalostí potrebných na uskutočnenie praktickej časti práce boli na základe tohto rozboru vypočítané zo signálov potrebné znaky. Tieto znaky boli podrobené štatistickej analýze a na jej základe boli vybrané niektoré znaky, ktoré boli vhodné ako vstup do neurónovej siete, ktorá je po naučení schopná triediť spánkové epochy do príslušných fáz.
|
|
|
Text mining in social network analysis
Hušek, Michal ; Mrázová, Iveta (advisor) ; Pešková, Klára (referee)
Title: Text mining in social network analysis Author: Bc. Michal Hušek Department: Department of Theoretical Computer Science and Mathematical Logic Supervisor: doc. RNDr. Iveta Mrázová, CSc., Department of Theoretical Computer Science and Mathematical Logic Abstract: Nowadays, social networks represent one of the most important sources of valuable information. This work focuses on mining the data provided by social networks. Multiple data mining techniques are discussed and analysed in this work, namely, clustering, neural networks, ranking algorithms and histogram statistics. Most of the mentioned algorithms have been implemented and tested on real-world social network data and the obtained results have been mutually compared against each other whenever it made sense. For computationally demanding tasks, graphic processing units have been used in order to speed up calculations for vast amounts of data, e.g., during clustering. The performed tests have confirmed lower time requirements. All the performed analyses are, however, independent of the actually involved type of social network. Keywords: data mining, social networks, clustering, neural networks, ranking algorithms, CUDA
|
|
|
New Techniques in Neural Networks Training - Connectionist Temporal Classification
Gajdár, Matúš ; Švec, Ján (referee) ; Karafiát, Martin (advisor)
This bachelor’s thesis deals with neural network and their use in speech recognition. Firstly,there is some theory about speech recognition, afterwards we show theory around neural networks in connection with connectionist temporal classification method. In next chapter we introduce toolkits, which were used for training of neural networks and also experiments done by them to find out impact of connectionist temporal classification method on precisionin phoneme decoding. The last chapter include summarization of work and overall evaluation of experiments.
|
|
|
Playing Gomoku with Neural Networks
Bako, Matúš ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The goal of this thesis is to create an artificial intelligence for playing Gomoku. While conventional methods usually use state space search combined with predefined rules, this artificial intelligence uses state space search and learned neural networks. A strategic network computes probability distribution for given a board state and a value network determines outcome of the game from a given board state. I trained multiple architectures of neural networks with different number of convolutional layers and different sizes of convolution kernels. Experiments show, that it is problematic to end a game without using the value network or search algorithm, but the strategic network can be used as a heuristic for choosing next move. Despite using relatively small dataset, created artificial intelligence is capable of beating weaker programs from Gomocup competition.
|
|
|
Stock Markets Analysis Using New Genetic Annealed Neural Network
Verner, Robert ; Baruník, Jozef (advisor) ; Vošvrda, Miloslav (referee)
The presented rigorosis thesis is focused on the stock markets returns analysis using a new type of neural network. First chapter of the thesis describes the underlying theory of the financial time series prediction, Efficient Market Hypothesis and conventional forecasting models. Following part illustrates biological framework, basic principles, functioning of neural networks, their architecture and several well-known learning algorithms such as Gradient descent, Levenberg-Marquardt algorithm or Conjugate gradient. It also mentions certain disadvantages which influence the performance and effectiveness of neural networks. Third chapter is devoted to two applied metaheuristic techniques, i.e. genetic algorithms and simulated annealing that were integrated into neural networks framework to eliminate above mentioned drawbacks. Next chapter describes details of presented hybrid network, whereas the last section is aimed at evaluation of overall results of all models. It shows that on the examined sample hybrid network clearly outperformed standard techniques as well as ordinary neural networks and in most cases achieved the least mean squared error among all explored methods. Keywords: stock returns analysis, neural networks, genetic algorithms, simulated annealing, hybrid networks JEL classification:...
|
|
|
Stock Markets Analysis Using New Genetic Annealed Neural Network
Verner, Robert ; Baruník, Jozef (advisor) ; Vošvrda, Miloslav (referee)
The presented master thesis is focused on the stock markets returns analysis using a new type of neural network. First chapter of the thesis describes the underlying theory of the financial time series prediction, Efficient Market Hypothesis and conventional forecasting models. Following part illustrates biological framework, basic principles, functioning of neural networks, their architecture and several well-known learning algorithms such as Gradient descent, Levenberg-Marquardt algorithm or Conjugate gradient. It also mentions certain disadvantages which influence the performance and effectiveness of neural networks. Third chapter is devoted to two applied metaheuristic techniques, i.e. genetic algorithms and simulated annealing that were integrated into neural networks framework to eliminate above mentioned drawbacks. Next chapter describes details of presented hybrid network, whereas the last section is aimed at evaluation of overall results of all models. It shows that on the examined sample hybrid network clearly outperformed standard techniques as well as ordinary neural networks and in most cases achieved the least mean squared error among all explored methods. Keywords: stock returns analysis, neural networks, genetic algorithms, simulated annealing, hybrid networks JEL classification:...
|
|
|
Classification Framework
Koroncziová, Dominika ; Otrusina, Lubomír (referee) ; Kouřil, Jan (advisor)
The goal of this work is the design and implementation of a machine learning software, based on the RapidMiner library. The finished application integrates the most commonly used algorithms and processes implemented in RapidMiner into an easily usable program. The application contains a simple command line interface, as well as a graphic interface to simplify selection of multiple parameters. The program also provides a tool to create standalone programs, that can be used for classification with a pre-trained model. On top of the original requirements the possibility to work with textual data from Wikipedia was also implemented, providing a tool for downloading and preprocessing of the data in order to use them as training input. This text focuses on the specifics of the algorithms and classifiers used and on their features and uses, and describes the design and implementation of the system. As part of this work, several tests were run in order to validate the efficiency and functionality of the program. The test results are included at the end of the thesis.
|
|
| |
guest ::
