|
|
Image similarity measuring using deep learning
Štarha, Dominik ; Šeda, Pavel (referee) ; Rajnoha, Martin (advisor)
This master´s thesis deals with the reseach of technologies using deep learning method, being able to use when processing image data. Specific focus of the work is to evaluate the suitability and effectiveness of deep learning when comparing two image input data. The first – theoretical – part consists of the introduction to neural networks and deep learning. Also, it contains a description of available methods, their benefits and principles, used for processing image data. The second - practical - part of the thesis contains a proposal a appropriate model of Siamese networks to solve the problem of comparing two input image data and evaluating their similarity. The output of this work is an evaluation of several possible model configurations and highlighting the best-performing model parameters.
|
|
| |
|
|
Graphical Educational System
Farbiak, Peter ; Seeman, Michal (referee) ; Štancl, Vít (advisor)
The goal of the theoretical part of this Bachelor's thesis is to introduce basics of learning psychology, principles of programming and algorithms and creating of graphical user interface to reader. Practical part is about creating program which demonstrates principles of basic algorithmic structures by adding graphical objects.
|
|
|
Visual Simulator and Debugger of Neural Networks
Beluský, Ondrej ; Zbořil, František (referee) ; Martinek, David (advisor)
Artificial neural networks represent computational parallel systems. This part of artificial intelligence is still researched. Basically neural network is the set of neurons, which are connected together. These networks have aspects of human intelligence, because they have an ability to learn. Their main goal is to simulate human brain, but creating such a network with large number of neurons and connections between them is impossible. They simulate some parts of human thinking. My task was to create visual simulator and debugger of these networks. The program was supposed to have a choice to debugging and stepping the algorithm for learning. My goal was also to implement editor, which allows creating and editing neural networks.
|
|
|
Algorithms for Computerized Optimization of Logistic Combinatorial Problems
Bokiš, Daniel ; Peringer, Petr (referee) ; Hrubý, Martin (advisor)
This thesis deals with optimization problems with main focus on logistic Vehicle Routing Problem (VRP). In the first part term optimization is established and most important optimization problems are presented. Next section deals with methods, which are capable of solving those problems. Furthermore it is explored how to apply those methods to specific VRP, along with presenting some enhancement of those algorithms. This thesis also introduces learning method capable of using knowledge of previous solutions. At the end of the paper, experiments are performed to tune the parameters of used algorithms and to discuss benefit of suggested improvements.
|
|
|
Abstract Syntax Tree Analysis for Python Teaching Support
Fáber, Jakub ; Škoda, Petr (referee) ; Smrž, Pavel (advisor)
The goal of this thesis is to create an analyzer system to check assignment solutions and to suggest improvements for them in terms of code quality and cleanliness. For the best results, a combination of static and dynamic analysis techniques is used. This system is implemented in the form of tutoring system and uses Docker containers for safe testing and analysis in an isolated environment. Interactive environment for communication with users is created with modern technologies such as Material Design.
|
|
|
Recognition of digits
Gorgol, Martin ; Hynčica, Tomáš (referee) ; Jirsík, Václav (advisor)
This work describes the basic concepts and principles in the field of neural networks. Closer then this work deals with the identification numbers using these networks, in particular, using the back-propagation method. There is a broken process of choosing a set of signs, types of symptoms and of choosing a neural network topology. The aim is to obtain specific results by using the program for working with neural networks.
|
|
|
A Library for Convolutional Neural Network Design
Rek, Petr ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
In this diploma thesis, the reader is introduced to artificial neural networks and convolutional neural networks. Based on that, the design and implementation of a new library for convolutional neural networks is described. The library is then evaluated on widely used datasets and compared to other publicly available libraries. The added benefit of the library, that makes it unique, is its independence on data types. Each layer may contain up to three independent data types - for weights, for inference and for training. For the purpose of evaluating this feature, a data type with fixed point representation is also part of the library. The effects of this representation on trained net accuracy are put to a test.
|
|
|
Object Recognition by Means of Evolutionary Methods
Lýsek, Jiří ; Škorpil, Vladislav (referee) ; Rábová, Ivana (referee) ; Šťastný, Jiří (advisor)
This thesis deals with usage of evolutionary methods, grammatical evolution particularly in application for object recognition in an image. Basic principles of object recognition and evolutionary methods with focus on grammatical evolution are described. The core of the thesis lies in design of techniques and methods for classifier programs creation using grammatical evolution. Also the designed fitness formula is presented. In the end, created testing and development environment in Java programming language is described.
|
|
|
Popularisation of Science in the Czech Republic
Holčapková, Martina ; Walek, Agata (referee) ; Baumgartnerová, Alena (advisor)
Bakalářská práce se zabývá tématem popularizace vědy. Cílem práce je definovat subjekty zabývající se popularizací vědy a zjistit informovanost veřejnosti o daném tématu. První část práce je zaměřena na definici termínu popularizace vědy. V druhé části jsou popsány rozdíly v učení dospělých a dětí. Třetí část ukazuje subjekty popularizace vědy a následující kapitola, založená na dotazníku, popisuje povědomí obyvatel Brna a jeho okolí o možnostech popularizace vědy. Závěrečná kapitola se věnuje tvorbě popularizačně naučného programu zaměřeného na téma elektřina a magnetismus.
|
guest ::
