|
|
Playing Games Using Neural Networks
Buchal, Petr ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this bachelor thesis is to teach a neural network solving classic control theory problems and playing the turn-based game 2048 and several Atari games. It is about the process of the reinforcement learning. I used the Deep Q-learning reinforcement learning algorithm which uses a neural networks. In order to improve a learning efficiency, I enriched the algorithm with several improvements. The enhancements include the addition of a target network, DDQN, dueling neural network architecture and priority experience replay memory. The experiments with classic control theory problems found out that the learning efficiency is most increased by adding a target network. In the game environments, the Deep Q-learning has achieved several times better results than a random player. The results and their analysis can be used for an insight to reinforcement learning algorithms using neural networks and to improve the used techniques.
|
|
|
Support for Organization of Festival Contests
Pavelek, Miroslav ; Kolář, Martin (referee) ; Křivka, Zbyněk (advisor)
This bachelor thesis is focused on making supporting information system for organization of contests on Animefest festival. It is a web application based on framework Django written in Python language. The system will replace the current web solution and will have new functionalities. For system administrator it provides the creationg and managing new contests and also for managing entries. Contestants will have the possibility to register to the contest and manage their entries.
|
|
|
Deep Neural Networks for Reinforcement Learning in Real-Time Strategy
Barilla, Marco ; Dobeš, Petr (referee) ; Kolář, Martin (advisor)
Machine learning is one of the fastest growing branches of modern science. It is a subfield of artificial intelligence research that is interested the problem of making computers help us solve complex modern problems. Games play an important role in this field because they represent the perfect environment for testing of new approaches and benchmarking against human performance. Starcraft 2 is currently in the spotlight, thanks to its broad playerbase and its complexity. The practical goal of this paper is to create an advantage actor critic agent that is able to operate in the environment of this game.
|
|
|
Deep Learning for Image Recognition
Munzar, Milan ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
Neural networks are one of the state-of-the-art models for machine learning today. One may found them in autonomous robot systems, object and speech recognition, prediction and many others AI tasks. The thesis describes this model and its extension which is used in an object recognition. Then explains an application of a convolutional neural networks(CNNs) in an image recognition on Caltech101 and Cifar10 datasets. Using this exemplar application, the thesis discusses and measures efficiency of techniques used in CNNs. Results show that the convolutional networks without advanced extensions are able to reach a 80\% recognition accuracy on Cifar-10 and a 37\% accuracy on Caltech101.
|
|
|
Generating training data with neural networks
Ševčík, Pavel ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this thesis was to prepare a training data set for traffic sign detection using generative neural networks. The solution uses a modified U-Net architecture and several experiments with the application of styles using AdaIN layers as in the StyleGAN model have been conducted. By extending the real GTSDB data set with the generated images, mean average precision of 80.36 % has been achieved, which yields an improvement of 19.27 % compared to the mean average precision of the detection model trained on real data only.
|
|
|
System with Servos Controlled by Microcomputer
Veselý, Miroslav ; Kolář, Martin (referee) ; Zemčík, Pavel (advisor)
The goal of this bachelor thesis was to investigate possibilities of controlling RC servos by amicrocomputer. A part of this thesis was creation of a device for purpose of browsing distant surfaceby a laser. The created device is based on Arduino platform and it is possible to control this deviceremotely by a computer application.
|
|
|
Application for Sport Group Management
Holcman, Jaroslav ; Tomešek, Jan (referee) ; Kolář, Martin (advisor)
This text describes the process of creating a mobile application for sport club management and its everyday operations. The main goal of the application is to digitize and unite most of common activities in the sport club. Another goal is to create the user interface which will be primarily intuitive and simple to use while providing straightforward ways of usage during most important user use cases. The thesis studies principles for designing user interfaces, analyzes sports team environment and defines the requirements for a software product to support sports club management. The design of the solution follows the analysis of requirements as well as the description of the implementation of the resulting product and its publishing to the real sports club environment. The thesis ends with description of user testing methods and results of the testing which validate accomplishment of defined goals.
|
|
|
Machinable bioceramics prepared by gelcasting method
Kolář, Martin ; Částková, Klára (referee) ; Trunec, Martin (advisor)
In the diploma thesis, overviews of the existing literature focused on the gelcasting method and based on the findings were prepared aqueous slurries of zirconium oxide for gelcasting method. These suspensions were examined for the influence of the content ceramics powder, type and content of dispersants and volume of initiator on viscosity of aqueous suspensions and process of polymerization. Optimum ceramic suspension had 45 vol.% of ceramic powder which was stabilized by 0,5 weight % of dispersant Dolapix CE 64. Polymerization running at room temperature was initiated by 0,175 weight % of ammonium persufate without accelerator. Microstructure of prepared ceramic blanks and sintered bodies was compared with body prepared by isostatic pressing. For the machining tests were prepared blanks in disc-shaped.
|
|
|
Virtual Waiting Room Data Base Storage
Sadloň, Matej ; Brejcha, Jan (referee) ; Kolář, Martin (advisor)
This thesis is part of project called Virtual Waiting Room. It is a cross-platform application which allows users to book a term with a provider without the need to personally wait in a waiting room. The thesis describes the design and implementation of database, library for work with this database, and a client for the administration of providers and waiting rooms. For this purpose, was used technologies such as MySQL, PHP and HTML.
|
|
|
Mobile System for Text Recognition on Android
Tomešek, Jan ; Kolář, Martin (referee) ; Zemčík, Pavel (advisor)
This thesis deals with creation of a mobile library for preprocessing of images with text which represents a part of a system for text recognition. The library is realized with emphasis on generality of use, efficiency and portability. The library providing a set of algorithms primarily for image quality assessment and text detection was created in this thesis. These algorithms enable a substantial decrease in volume of transmitted data and speed up and refinement of the recognition process. An example application for the Android platform able to analyze composition of foods stated on their wrappings was created as well. Overall, the library (system) simplifies development of mobile applications with focus on text extraction and analysis. The mobile application then provides a comfortable way of food harmfulness verification. The thesis offers a reader an overview of current solutions and tools available in this field, it provides a breakdown of important image preprocessing algorithms and guides him through the construction of the library and the application for mobile devices.
|
guest ::
RSS feed.