National Repository of Grey Literature 275 records found  1 - 10nextend  jump to record: Search took 0.00 seconds. 
Simulations of open-ended evolution
Prax, Sebastian ; Toman, Jan (advisor) ; Tureček, Petr (referee)
Evolutionary algorithms are used to solve a number of optimization problems in the computer science. At the same time, they are fundamental pillar for creating evolutionary simulations and testing scientific hypotheses in a various areas of theoretical biology. In the first half of my work, I characterize the concept of "open-ended evolution", focus on its connection with the technical side of simulations and introduce readers to the problematics of system simulation. Further on, I deal with the phenomenon of increasing complexity and the idea of "evolutionary progress". All these topics are confronted with various perspectives of researchers in the field of evolutionary biology. In the second half, I summarize the benefits of existing projects for evolutionary biology and applied informatics, as well as the ways in which the simulations of open-ended evolution can be approached. Basically, these projects can be divided into two categories. They are either projects in which individuals develop towards a predefined goal, which is conditioned by a fitness function, or projects of researchers who seek to achieve an open-ended evolution by employing biologically realistic design of the genetic code and environment in conjunction with the absence of a particular attractor in the evolution of virtual...
Artificial Intelligence for the Dominion Game
Babušík, Jan ; Pilát, Martin (advisor) ; Gemrot, Jakub (referee)
The subject of this thesis is an artificial intelligence for the Dominion card game, which is usable in a two-player game. Dominion is characterized by the fact that there is a large number of initial configurations. The artificial intelligence selects the best strategies from a set of prepared strategies so that the time it takes to generate a specialized strategy does not delay players from every game. This approach has been implemented with emphasis on game extendability. In the design of the artificial intelligence evolutionary algorithms were used. The work also includes an implementation of the game itself in the C# language and a simple graphical interface for playing the game. 1
Simplified Versions of Chess for the Teaching of the Game
Hübsch, Anna ; Pilát, Martin (advisor) ; Zelinka, Mikuláš (referee)
Despite its age, chess is still one of the most popular and most played board games. Nowadays, it is more and more common to train even little children and simplified versions of chess are often used for that. The pur- pose of this thesis is to create an application for training of children and to compare various methods of artificial intelligence. In the thesis the Monte Carlo Tree Search, Minimax and Alpha-beta pruning algorithms are com- pared. The thesis also contains comparison of multiple evaluation functions. Few most common simplified versions of chess and also Fischer chess are available in the application. The theoretical part of the thesis contains basic information about chess and chess training, history of computer chess and description of used algorithms. There is also a comparison of implemented algorithms both according to their level of play and according to their usa- bility for training purposes. One of the interesting outcomes of the thesis is an observation that during the game the value of different figures changes and that in endgames the classical chess evaluation function is worse than evaluation function produced by an evolutionary algorithm. 1
Real-time strategy with an interface for artificial intelligence
Červinková, Kateřina ; Pilát, Martin (advisor) ; Gemrot, Jakub (referee)
This thesis focuses on a real-time strategy called Skillegy, which, in contrast to the majority of games of similar kind, uses only one type of unit. However, these units have certain abilities whose levels can increase depending on their actions or using upgrading in buildings. The game can be played by multiple players over network and it includes an interface for an artificial intelligence with example implementation that can be used instead of a human opponent. The game is created in the Unity engine with use of the C# language and the .NET Framework. 1
Interconnection of Recent Strategic Games with Multi-Agent Frameworks
Válek, Lukáš ; Kočí, Radek (referee) ; Zbořil, František (advisor)
This thesis is focused on design of framework for creation an articial opponents in strategy games. We will analyze different types of strategy games and artificial intelligence systems used in these types of games. Next we will describe problems, which can occur  in these systems and why agent-based systems makes better artificial opponents. Next we will use knowledge from this research to design and implement framework, which will act as support for creating an artificial intelligence in strategy games.
Strategic Game Based on Multiagent Systems
Knapek, Petr ; Kočí, Radek (referee) ; Zbořil, František (advisor)
This thesis is focused on designing and implementing system, that adds learning and planning capabilities to agents designed for playing real-time strategy games like StarCraft. It will explain problems of controlling game entities and bots by computer and introduce some often used solutions. Based on analysis, a new system has been designed and implemented. It uses multi-agent systems to control the game, utilizes machine learning methods and is capable of overcoming oponents and adapting to new challenges.
Simplified Multiplication in Convolutional Neural Networks
Juhaňák, Pavel ; Jaroš, Jiří (referee) ; Sekanina, Lukáš (advisor)
This thesis provides an introduction to classical and convolutional neural networks. It describes how hardware multiplication is conventionally performed and optimized. A simplified multiplication method is proposed, namely multiplierless multiplication. This method is implemented and integrated into the TypeCNN library. The cost of the hardware solution of both conventional and simplified multipliers is estimated. The thesis also introduces software tools developed to work with convolutional neural networks and datasets used to test them in the image classification task. Test architectures and experimentation methodology are proposed. The results are evaluated, and both the classification accuracy and cost of the hardware solution are discussed.
Chatbot in an Enterprise Information System
Novák, Miroslav ; Rychlý, Marek (referee) ; Kreslíková, Jitka (advisor)
This diploma thesis deals with problems of development of chatbots. The theoretical part of the thesis introduces the concept of the conversational interface in general and analyzes available technologies for its development. The practical part deals with the design and implementation of a particular chatbot, whose goal is to be a virtual assistant in the process of selecting and purchasing goods. This is accomplished by connecting the chatbot to the product information management system using OData web services. One of the biggest problems was to determine the order of questions asked about product properties. For the implementation was used decision tree theory.
Artificial Intelligence Document Classification
Molnár, Ondřej ; Kačic, Matej (referee) ; Třeštíková, Lenka (advisor)
This paper deals with document classification using artificial intelligence. It describes the principles of classification and machine learning. It also introduces AI methods and presents Naive Bayes classification method in detail. Provides practical implementation of the classifier in MS Office and discusses other possible extensions.
Reconstruction of Facial Images Using Neural Networks
Zubalík, Petr ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
The main purpose of this bachelor's thesis is to propose and implement a model, using neural networks, that will be able to reconstruct low-resolution facial images with blurry parts of the face. The task of super-resolution of facial images is solved by two models based on convolutional neural networks. The first model is built upon the architecture of ResNet whereas the other model makes use of the principles of generative adversarial networks. The proposed models are implemented in the Python programming language with the use of application programming interface of the TensorFlow framework. Moreover, as a part of this work, an application with a simple grafical user interface was created. This application makes it easy to use the implemented models. Several experiments are analyzed in the last chapter of this thesis to evaluate the performance of the models.

National Repository of Grey Literature : 275 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.