|
|
Playing Gomoku with Neural Networks
Slávka, Michal ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
Táto práca sa zaoberá použitím algoritmu AlphaZero pre hru Gomoku. AlphaZero je založený na spätnoväzbnom učení a k trénovaniu nemusia byť využité žiadne existujúce datasety. Trénovanie prebieha iba na hrách algoritmu samého so sebou. AlphaZero používa algoritmus na prehľadávanie stromu, pre zlepšenie stratégie. Na vylepšnej stratégii sa následne trénuje neurónová sieť. Tento prístup bol úspešný v hrách proti existujúcim algoritmom. Generovanie trénovacích dát vysokej kvality si vyžaduje veľa výpočetne náročných iterácií trénovania a generovania dát. Experimenty ukázali, že každou iteráciou sa algoritmus zlepšuje, čo naznačuje, že je ešte miesto na zlepšenie, ale množstvo iterácií nedostačovalo na to, aby bol poriadne natrénovaný.
|
|
|
Fusion of Radar and Visual Data for Remote Sensing
Strych, Tomáš ; Beran, Vítězslav (referee) ; Kolář, Martin (advisor)
Cieľom práce je vygenerovať satelitný optický snímok v prípade jeho nedostupnosti. Takýto snímok je vygenerovaný z aktuálneho radarového snímku a za pomoci radarových a optických snímkov z minulosti. Zameranie práce cieli na poľnohospodárstvo, kde sa na analýzu dát používajú rôzne vegetačné indexy. Pre zjednodušenie problematiky je práca zameraná len na optický snímok zobrazujúci NDVI. Boli vytvorené 4 dátové sady, pre prvé tri ročné obdobia a~štvrtý, ktorý ich spája. Pre riešenie problému preloženia obrázku z jedného na druhý bol použitý model Pix2Pix-cGAN. Výsledky práce zobrazujú rozdiely pri použití dátových sád, rozličného množstva a~typu použitých snímkov, tak ako aj intervalu medzi snímkami. Daným výskumom bolo zistené, že sieť je schopná vytvárať reálne uveriteľné obrázky s validnými numerickými hodnotami, avšak má problém správne využiť informáciu o radarovej zmene, ktorá je dôležitá pre ohodnotenie vývoja rastlín práve v prípade nedostupnosti optického snímku. Táto práca a~jej výsledky sú jedinečné vďaka naprieč Európou geograficky rozmanitej dátovej sade a vďaka zameraniu na agrikultúru, a to bez ohľadu na typ plodín.
|
|
|
Machine Learning Strategies in Electronic Trading
Huf, Petr ; Kolář, Martin (referee) ; Černocký, Jan (advisor)
Úspěšné obchodování na trzích je snem mnoha lidí. Zajímavým odvětvím tohoto byznysu je elektronické obchodování, kde obchodní strategie běží na počítači bez jakéhokoliv zásahu člověka. Tento způsob obchodování poskytuje spoustu volného času a vysoké příjmy. Tato práce je zaměřena na využití neuronových sítí při stavbě takovéto obchodní strategie. Jako základ byla použita již existující rekurentní neuronová síť, která byla postupně modifikována podle potřeb pro obchodování. Výsledkem je neuronová síť předpovídající budoucí pohyby trhu. Obchodní strategie používající tuto neuronovou síť dokáže na burze úspěšně obchodovat.
|
|
|
Mobile App for Making Challenges and Taking Part in Them
Plachý, Tomáš ; Kolář, Martin (referee) ; Herout, Adam (advisor)
This thesis deals with the problematics of designing, implementing and testing of mobile application for operationg systems iOS and Android. The main work of this thesis is development of an application, which allows its users to create challenges and invite their friends to participate in them. Users can also watch the progress of other participants in a challenge, which can give themselve more motivation to complete the challenge. The application was designed and developed with focus on opinions of its users. I have started by developing a prototype in order to find out, which functions do the users find the most crucial. Thereafter I created the first official version, which was subsequently iteratively improved with regard to feedback from testers.
|
|
|
Parametric 3D Models
Ondrejó, Michal ; Kolář, Martin (referee) ; Zemčík, Pavel (advisor)
The aim of this work is to propose possibilities of interconnection of objects in parametric model. Individual options are implemented in the parametric three-dimensional modeling system. This system allows the creation of models using various geometric operations, change parameters at any time, animate the created model, and save the parametric model in a human-readable format. The proposed solution was implemented and evaluated on simple example.
|
|
|
System for Import/Management of Photos
Škutová, Sára ; Kolář, Martin (referee) ; Zemčík, Pavel (advisor)
The goal of this bachelor thesis was to create an application that would allow categorize photo-graphs into groups and then search for their duplicates. Sorting and identification of identical photos is based on Exif metadata. The result is a standalone application that has been programmed using C++, Qt framework, and Exiv2 library. The functionality of the program was verified with a photo package and the user interface was tested with the help of users.
|
|
|
Web Application for Intuitive Composition of Text Filters
Sadílek, Jakub ; Kolář, Martin (referee) ; Herout, Adam (advisor)
The aim of this thesis is to provide intuitive and easy to use tool for advanced text filtration with the option of easy prototyping and tuning, without the necessity to know programming techniques. The basic principle is the choice of text tools and their inserting into the sequence, so called pipeline, which is typical for shell, from which the application draws inspiration. Tools can be also additionally edited or swapped. The application is aimed primarily at users unfamiliar with this principle or at programmers, for whom it is time-efficient to have their text modified this way and afterwards generate equivalent shell expression. Another way of tuning is realized using so called breakpoints, through which it is easy to quickly focus on chosen lines of the text. This way, the application offers functionality in two separated modes, between which the users can switch anytime according to their needs.
|
|
|
A Tool for Sharing and Visualization of Skydiving Records
Madaj, Tomáš ; Kolář, Martin (referee) ; Herout, Adam (advisor)
Purpose of this work is to create a web application which would enable easiest possible 3D visualisation and sharing of uploaded GPS logs. It is intended mainly for aerosports. The application is built on the full-stack JavaScript platform Meteor.js, it features a web user interface and utilizes WebGL library three.js for 3D visualisations in browser. This form allows to achieve intended accessibility and simplicity of usage. The application is a valuable sports performance analysis tool. It brings accurate view of the actual trajectory in the sky where it's otherwise impossible due to the absence of a close visual reference point.
|
|
|
Mobile App for Viewing Internet Pictures
Kočnar, David ; Kolář, Martin (referee) ; Herout, Adam (advisor)
This thesis explains issues concerning the development of mobile applications for Android and describes a complete design and development of mobile application Impres for image viewing. In addition to the mobile application there was also created a server application in PHP providing data from different internet sources. Taken together this service aims to bring to its user an inspiring content consisting of phototography and other visual art. The service will automatically add new content and create user-personalised selection. The work also describes theoretical knowledge and procedures necessary for technical design and development of mobile applications. Conclusion evaluates solution and proposals for possible other features.
|
|
|
Learning to Generate Images with Convolutional Neural Networks
Kohút, Jan ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this Bachelor's thesis is to design and analyze convolutional neural networks generating images of characters based on their parameters. Parameters of characters are type of char, font, colour of character, background colour, translation and rotation. Neural networks have created multidimensional representation of each parameter. Relations inside these representation are similar to relations inside parameters. Neural networks generate characters with new values of parameters based on interpolation between learned values of parameters. Neural networks are capable to generalize problem of generating images.
|
guest ::
