|
|
Application of Neural Networks for Human Face Localization
Žák, Jakub ; Štancl, Vít (referee) ; Švub, Miroslav (advisor)
This paper describes aplication of multi layered neural network for solving problem of detection human face in static picture. This Method has good generalizational capabilities in general and there is no need to assembly complex models of analyzed data. There is also mentioned posibility of using neural network with changed architecture in this work.
|
|
|
Elliot Wave Detection
Kaleta, Marek ; Šperka, Svatopluk (referee) ; Petřík, Patrik (advisor)
This work deals with Elliott wave detection, which are statistical tool used to describe financial makret cycles and predict market trends. The work proposes methods to detect Elliott Waves and evaluetes them. From several methods of Elliott wave detection, Committee machines of multilayer perceptrons are used. Result of this work is a program, which detect Elliott impulse waves on input signal and builds hierarchy of Elliott waves.
|
|
|
Neural Network Number Recognition
Doupovec, Zdeněk ; Juránek, Roman (referee) ; Šilhavá, Jana (advisor)
This work describes the basic concepts and principles in the field of neural networks. Closer then deals with the problem of multilayer perceptron networks, namely back-propagation method. There are analyzed the advantages and disadvantages of these methods, the proposal of possible digits recognition system using back-propagation. The aim is to obtain concrete results from the program whitch is able to recognize numbers.
|
|
|
Artificial Intelligence-Based Player for "Blokus" Game
Sulaiman, David ; Hrubý, Martin (referee) ; Rogalewicz, Adam (advisor)
This thesis compares forward neural networks with algorithms using game theory on basis of board game Blokus. The theoretical introduction part describes the characteristics of neural networks and work with them. There is also outlined algorithm of game theory. The second part deals about the implementation of players based on the outlined principles and shortly descriptions GUI of application. In conclusion, the differences between the players are evaluated on the charts created on the performed tests.
|
|
|
Simple Character Recognition
Duba, Nikolas ; Svoboda, Pavel (referee) ; Polok, Lukáš (advisor)
This thesis is focused on optical character recognition and its processing. The goal of this application is to make it possible easily track daily expenses. It can be used by an individual or by a company as a monitoring tool. The main principle is to make this tool most as user friendly as it can be. The application gets its input from hardware, such as a scanner or camera, and analyzes the content of the cash voucher for further processing. To analyze the voucher, the application employs different optical character recognition methods. The result is subsequently parsed. Detailed explanations of used methods are inside the document. The application output is a filled database with cash voucher details. Another part of the work is an information system with the main purpose of displaying the collected data.
|
|
|
Keyword Spotting Implementation to Mobil Phone (Symbian 60)
Cipr, Tomáš ; Schwarz, Petr (referee) ; Szőke, Igor (advisor)
Keyword spotting is one of the many applications of automatic speech recognition. Its purpose is determining spots in given utterance in which some of the specified words were spoken. Keyword spotting has a great potential to enhance performance of new applications as well as the existing ones. An example could be a mobile phone voice control. Due to OS Symbian's coming to the market it is even possible for end user to implement a keyword spotting for a mobile phone on his or her own. The thesis describes theoretical prerequisites for keyword spotting and its implementation. Firstly the OS Symbian is presented with respect to the given task. Secondly each step of keyword spotting process is described. Finally the object design of keyword spotter is presented followed by implementation description. The thesis concludes with results review and notes on possible improvements.
|
|
|
Deep Neural Networks
Habrnál, Matěj ; Zbořil, František (referee) ; Zbořil, František (advisor)
The thesis addresses the topic of Deep Neural Networks, in particular the methods regar- ding the field of Deep Learning, which is used to initialize the weight and learning process s itself within Deep Neural Networks. The focus is also put to the basic theory of the classical Neural Networks, which is important to comprehensive understanding of the issue. The aim of this work is to determine the optimal set of optional parameters of the algori- thms on various complexity levels of image recognition tasks through experimenting with created application applying Deep Neural Networks. Furthermore, evaluation and analysis of the results and lessons learned from the experimentation with classical and Deep Neural Networks are integrated in the thesis.
|
|
|
Neural-Fuzzy Systems
Dalecký, Štěpán ; Samek, Jan (referee) ; Zbořil, František (advisor)
The thesis deals with artificial neural networks theory. Subsequently, fuzzy sets are being described and fuzzy logic is explained. The hybrid neuro-fuzzy system stemming from ANFIS system is designed on the basis of artificial neural networks, fuzzy sets and fuzzy logic. The upper-mentioned systems' functionality has been demonstrated on an inverted pendulum controlling problem. The three controllers have been designed for the controlling needs - the first one is on the basis of artificial neural networks, the second is a fuzzy one, and the third is based on ANFIS system. The thesis is aimed at comparing the described systems, which the controllers have been designed on the basis of, and evaluating the hybrid neuro-fuzzy system ANFIS contribution in comparison with particular theory solutions. Finally, some experiments with the systems are demonstrated and findings are assessed.
|
|
|
Progressive Usage of Neural Networks in Telecommunication
Babnič, Patrik ; Kacálek, Jan (referee) ; Škorpil, Vladislav (advisor)
The main task of the Master Thesis is introduction into network elements in converget networks. Great importance is put on network elements today, that is why priority resolving is crucial. Theorethical part deals with network elements and neuron networks. Neuron networks were analysed from history to present. The main goal was to develop a neuron network topology able to manage a network element. The developed topology consists of four-layered perceptron network with four inputs and one output. The simulation was carried out on MATLAB software. No real data were used in the simulation. All input values were generated by MATLAB software hence it was a simulation.
|
|
|
Usage of the MATLAB environment for neural networks
Lenk, Peter ; Atassi, Hicham (referee) ; Škorpil, Vladislav (advisor)
This bachelor thesis discusses the basic theory and modelling of neural networks in the software environment of MATLAB. The thesis can be divided into four parts. After an introduction into the thesis, the theoretical background of the neural netwoks is explained in the first chapter. This chapter features a brief history and a biological background of neural networks and deals with the basic network architectures and the training processes. The next part is the description of how to implement networks in a general way using the MATLAB enviroment, so it deals with preparation of data, creation, simulation and training of a neural network. The last part of the paper covers a design of two excersises created in order to introduce modelling of the neural networks in the MATLAB enviroment to the students.
|
guest ::
