|
| |
|
| |
|
|
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.
|
|
|
Reinforcement Learning for Bomberman Type Game
Adamčiak, Jakub ; Beran, Vítězslav (referee) ; Hradiš, Michal (advisor)
This bachelor's thesis aims to develop, implement and train reinforcement learning models for a Bomberman-type game. It is based on Bomberland environment from CoderOne. This environment was created for education and research in the field of artificial intelligence. In this thesis I tackle the settings and problems of implementing agent into the environment. I used 2 policies (MLP and CNN), 2 algorithms (PPO and A2C) and 5 setups of neural networks for feature extraction with the use of libraries stable baselines 3 and pytorch. Total training time resulted in 1207 real-world hours, 4168 computing hours and 271 milions of time steps. Although the training was not successful, this thesis shows the process of implementing a reinforcement learning model into a Gym environment.
|
|
|
Robotic Tracking of a Person using Neural Networks
Zakarovský, Matúš ; Lázna, Tomáš (referee) ; Žalud, Luděk (advisor)
Hlavným cieľom práce bolo vytvorenie softvérového riešenia založeného na neurónových sieťach, pomocou ktorého bolo možné detegovať človeka a následne ho nasledovať. Tento výsledok bol dosiahnutý splnením jednotlivých bodov zadania tejto práce. V prvej časti práce je popísaný použitý hardvér, softvérové knižnice a rozhrania pre programovanie aplikácií (API), ako aj robotická platforma dodaná skupinou robotiky a umelej inteligencie ústavu automatizácie a meracej techniky Vysokého Učenia Technického v Brne, na ktorej bol výsledný robot postavený. Následne bola spracovaná rešerš viacerých typov neurónových sietí na detekciu osôb. Podrobne boli popísané štyri detektory. Niektoré z nich boli neskôr testované na klasickom počítači alebo na počítači NVIDIA Jetson Nano. V ďalšom kroku bolo vytvorené softvérové riešenie tvorené piatimi programmi, pomocou ktorého bolo dosiahnuté ciele ako rozpoznanie osoby pomocou neurónovej siete ped-100, určenie reálnej vzdialenosti vzhľadom k robotu pomocou monokulárnej kamery a riadenie roboty k úspešnému dosiahnutiu cieľa. Výstupom tejto práce je robotická platforma umožnujúca detekciu a nasledovanie osoby využiteľné v praxi.
|
|
| |
|
| |
|
|
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.
|
|
|
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.
|
|
|
Face Recognition with Acceleration on the Neural Compute Stick
Horník, Matej ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
This bachelor thesis deals with current techniques for recognizing people by face. Convolutional neural networks are currently used for face recognition. In this work, convolutional neural networks will be described and also the architectures of convolutional networks used for face recognition will be compared. The goal will be to create a built-in system that will consist of a camera, a computing unit and a Neural Compute Stick accelerator. The system will recognize people by face with a freely available algorithm.
|
guest ::
