|
|
Self-Modifying Cellular Automata
Szabo, Peter ; Drábek, Vladimír (referee) ; Bidlo, Michal (advisor)
This work deals with cellular automata with a concept of self- modification and their comparsion against regular cellular automatons . For this task we constructed a simulator , that lets us define the logic of artificial inteligence, number generator and statistical test, which are used by the automata , on their own . Consequently two experiments are carried out that demonstrate the concept of self- modification .
|
|
|
The Use of Means of Artificial Intelligence for the Decision Making Support on Stock Market
Vaško, Jan ; Kříž, Jiří (referee) ; Dostál, Petr (advisor)
Diploma thesis deals with analyzing the possibility of using artificial intelligence, specifically artificial neural networks and fuzzy logic, on the capital markets as a tool to support decision making in business. The Matlab software is used for this purpose. The work is divided into three parts. The first part deals with theoretical knowledge, brief description of the current situationin is covered in a second part and the theoretical solutions are applied to the system in the third section.
|
|
|
Methods of deep learning in image processing tasks
Polášková, Lenka ; Marcoň, Petr (referee) ; Mikulka, Jan (advisor)
The clue of learning to recognize objects using neural network lies in imitation of animal neural network's behavior. In spite the details of how brain works is not known yet, the teams consisting of scientists from various medical or technical professions are trying to search for them. Thanks to giants like Geoffrey Hinton science made a big progress in this domain. The convolutional networks which are based on animal model of optical system can be advantageously used for image segmentation and therefore they ware chosen for segmentation of tumor and edema from images of magnetic resonance. The models of artificial neural networks used in this work had achieved the 41\% of success in edema segmentation and 79\% in segmentation of tumor from brain issue.
|
|
|
Word2vec Models with Added Context Information
Šůstek, Martin ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
This thesis is concerned with the explanation of the word2vec models. Even though word2vec was introduced recently (2013), many researchers have already tried to extend, understand or at least use the model because it provides surprisingly rich semantic information. This information is encoded in N-dim vector representation and can be recall by performing some operations over the algebra. As an addition, I suggest a model modifications in order to obtain different word representation. To achieve that, I use public picture datasets. This thesis also includes parts dedicated to word2vec extension based on convolution neural network.
|
|
|
Creating a knowledge base for the diagnosing of diseases
Macháček, Daniel ; Steinerová, Kateřina (referee) ; Jirsík, Václav (advisor)
This bachelor thesis is focused on problematic of creation knowledge base. It is describing basics of expert systems, their function and possible usage in modern world. In result of this thesis is knowlenge base in web aplication NPS able to diagnose diseases of hematology-oncology and that is proving possibility for use in real life. Knowledge base was created in cooperation with experts in the medical field and contains real data.
|
|
|
Artificial Intelligence in Modern Computer Games
Pavliska, Jiří ; Zuzaňák, Jiří (referee) ; Mikolov, Tomáš (advisor)
The aim of this bachelor's thesis is to propose an artificial inteligence that could be used to create a modern computer game. My intention is to introduce the termin Artificial Inteligence to the reader. I include the description of elements and techniques used for determining the behavior of figures that are controlled by a computer. I am also focusing the abilities of the program to search the state space and to find the shortest possible way.
|
|
|
Artificial Intelligence in Strategic Computer Games
Votroubek, Lukáš ; Přibyl, Bronislav (referee) ; Zuzaňák, Jiří (advisor)
This work covers with artificial intelligence of strategy computer games, however many of these methods are usable in other areas. These are different methods used in deciding (finite state machina, fuzzy logic, Markov Process), planning (Goal-oriented action planning, Montecarlo planning, Case-based planning) and machine learning ( Reinforcement leasing, Decision Learning and Neural Networks). Objective of this thesis is to study this methods from different sources and explain their base principle. Then few of this methods resolve in more details and implement them (goal oriented planning and state machine). This thesis focuses on game engine ORTS, which is used in implementing and testing methods.
|
|
|
E-learning study modules
Kosík, Tomáš ; Honzík, Petr (referee) ; Jirsík, Václav (advisor)
This master’s thesis is focused on description of e-learning by electronic form of teaching as a way of modern education. In theoretical part various forms, possibilities and basic structures of electronic education systems are described. It presents thorough analyses of positives and negatives of e-learning, both, from a technical perspective as well as from social point of view. In the second part of this thesis, the reader becomes familiar with e-learning system AI Tools used by UAMT FEEC VUT in Brno to support the teaching of basics of artificial intelligence. Furthermore, the work deals with the creation of three plug-in modules for this computer programme. These modules are programmed in C# and pursue matters of informed and uninformed state space search, and issues of forward and backward chaining used in expert systems. In conclusion, the results of theoretical and practical work are evaluated
|
|
|
Design of Trading Strategy for Managing of Free Financial Capital of the Company
Jiřík, Leoš ; Dufek, Ladislav (referee) ; Budík, Jan (advisor)
This thesis deals with the design of trading strategies suitable for trading the currency markets. Design is carried out by means of artificial intelligence, the proposed strategies are then optimized and evaluated using previously unknown data. The partial objective is to implant this process in an existing company with the aim to broaden its capital. The consequences arising from this trading approach to the development of the company’s capital are subsequently studied from several perspectives – a schedule is outlined for the introduction into the company that has been chosen earlier, then the expected costs and revenues are compared in the scope of medium-term and in the last part the above procedure is analyzed so its risks can be pointed out and therefore procedures for their restrictions can be proposed as well.
|
|
|
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.
|
guest ::
