|
|
Chess Program with Various Chess Variations with Various Set of Figures
Škandera, František ; Žák, Jakub (referee) ; Rozman, Jaroslav (advisor)
The goal of this thesis was to create a chess program able to play various chess variations with various set of figures. The first part of the work deals with the general matters of creating a chess program and implementing a chess artificial intelligence. In the second part we analyze individual chosen chess variations and suggest strategies for their implementation. Eventually we describe the implementation of the created application itself and its structure.
|
|
|
Simulation Based Matchmaking Optimisation
Eštvan, Ivan ; Chlubna, Tomáš (referee) ; Milet, Tomáš (advisor)
This bachelor's thesis focuses on designing a working matchmaking system and simulation environment for a First Person Shooter like game and their implementation within Unreal Engine 4. It introduces various types of matchmaking systems used in today's games and explains some basic concepts used in Unreal Engine 4 to implement such environments. Implemented system then takes the input data, with information about players, creates matches by using our own matchmaking and performs a simulation of them, providing the simulation results of created matches for further analysis.
|
|
|
Exploiting Approximate Arithmetic Circuits in Neural Networks Inference
Matula, Tomáš ; Mrázek, Vojtěch (referee) ; Češka, Milan (advisor)
Táto práca sa zaoberá využitím aproximovaných obvodov v neurónových sieťach so zámerom prínosu energetických úspor. K tejto téme už existujú štúdie, avšak väčšina z nich bola príliš špecifická k aplikácii alebo bola demonštrovaná v malom rozsahu. Pre dodatočné preskúmanie možností sme preto skrz netriviálne modifikácie open-source frameworku TensorFlow vytvorili platformu umožňujúcu simulovať používanie approximovaných obvodov na populárnych a robustných neurónových sieťach ako Inception alebo MobileNet. Bodom záujmu bolo nahradenie väčšiny výpočtovo náročných častí konvolučných neurónových sietí, ktorými sú konkrétne operácie násobenia v konvolučnách vrstvách. Experimentálne sme ukázali a porovnávali rozličné varianty a aj napriek tomu, že sme postupovali bez preučenia siete sa nám podarilo získať zaujímavé výsledky. Napríklad pri architektúre Inception v4 sme získali takmer 8% úspor, pričom nedošlo k žiadnemu poklesu presnosti. Táto úspora vie rozhodne nájsť uplatnenie v mobilných zariadeniach alebo pri veľkých neurónových sieťach s enormnými výpočtovými nárokmi.
|
|
|
Algorithmic Trading Using Artificial Neural Networks
Poláček, Samuel ; Beneš, Karel (referee) ; Szőke, Igor (advisor)
Algorithmic trading of many kinds of assets is not a new field at all. Domain of neural networks provides many tools, which are usefull in this field. This bachelor thesis discusses cryptocurrency trading algorithms using artificial neural network. In theoretical section of this thesis the basic theory and terms the stock market trading is based on is discussed. After the basic idea of cryptocurrencies is defined and used technical tools are introduced, the practical section starts. Sufficient configuration of neural network topology and hyperparameters values are obtained by many experiments. Subsequently after many experiments with indicators of technical analysis, acceptable neural network input configuration is obtained. Created neural network model combined with defined trading strategy generates profit.
|
|
|
Deep Neural Network Optimization
Bažík, Martin ; Wiglasz, Michal (referee) ; Sekanina, Lukáš (advisor)
The goal of this thesis was to design, implement and analyze various optimizations of deep neural networks, in order to improve the observed parameters. The optimizations are based on modification of the data representation used by neural network operations and searching for the best combination of its hyper-parameters. The convolutional neural networks used for these optimizations were built on LeNet-5 architecture and trained on MNIST, CIFAR-10, and SVHN datasets. The neural networks and their optimizations were implemented within Tiny-dnn library using C++ programming language.
|
|
|
Creating the Game Strategies for PuppetWars Using Neuroevolution
Šmelko, Adam ; Pilát, Martin (advisor) ; Matzner, Filip (referee)
In recent years the gaming industry has been on increase. In order to maintain competitiveness gaming companies are required to develop more and more compelling computer games what implies the presence of the very responsive artificial intelligence controlling the game elements, on which our work focuses. We have implemented a simple 2D programming game where we have experimented with the artificial intelligence in it trying to create a strategy beeing able to compete with human. We have explored several variations of learning through the evolutionary strategy applied to neural networks and we have created game characters worthy of being an equal opponent to the game user.
|
|
|
Domain Specific Languages in Functional Programming
Rapavá, Jana ; Hric, Jan (advisor) ; Pilát, Martin (referee)
In Artificial Intelligence, especially in area of constraint programming, it's popular to design various modeling languages which allow solving problems on domain level and by using domain specific abstractions. Techniques known from research on Domain-Specific Languages are often useful in this effort. Functional programming languages offer new tools for designing such languages, particularly Domain-Specific Embedded Languages. This work investigates the advantages and disadvantages of using functional programming for designing and implementing a Domain-Specific Embedded Language for state space search problems.
|
|
|
The Use of Artificial Intelligence for Decision Making
Nezbedová, Katarína ; Pekárek, Jan (referee) ; Dostál, Petr (advisor)
This bachelor thesis deals with the Tamari attractor problem and its application for forming a prediction model. The core of the work is to create a simulation program in the MATLAB development environment and to use it to create and compare several case studies of a predictive model based on different parameters. This model is graphically illustrated and supplemented by economic interpretation.
|
|
|
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.
|
|
|
Evolutionary Analogue Amplifier Optimisation
Bielik, Marek ; Zachariášová, Marcela (referee) ; Bidlo, Michal (advisor)
Táto práca demonštruje možnosti využitia evolučných algoritmov, konkrétne evolučných stratégií, v doméne dizajnu analógových zosilňovačov. Do implementácie je zahrnutý ngSPICE simulátor, ktorý je použitý na vyhodnotenie optimalizovaných riešení a v práci je navrhnutých niekoľko vyhodnocovacích metód. Práca tiež zahŕňa experimenty a ich výsledky, ktoré boli použité na určenie najvodnejších parametrov evolučných stratégií. Cieľom bolo optimalizovať hodnoty súčiastok jedno a dvoj stupňových zosilňovačov s bipolárnymi tranzistormi v zapojení so spoločným emitorom. Výsledkom je nástroj umožňujúci návrh zosilňovačov s ľubovoľným zosilnením v rámci možností daného obvodu bez použitia akéhokoľvek matematického aparátu.
|
guest ::
