|
|
Technical analysis of stock trends using artificial neural networks
John, Pavel ; Petříčková, Zuzana (advisor) ; Pilát, Martin (referee)
Although the discipline has not received the same level of acceptance in the past, the technical analysis has been part of financial practice for centuries. One of the big issues was the absence of widely respected fully rational background that is necessary for the modern science. The presence of geometrical shapes recognized by a human eye in historical data charts remained as one of the most important tools till the last decades. Nowadays, it is possible to find commercial trading software which employs neural networks. However, a freely accessible tool is difficult to obtain. The aim of this work was to investigate the usability of applications of neural networks on the technical analysis and to develop a software tool that would implement the knowledge acquired. An application was created and a new promising trading strategy proposed along with experimental data. The advantages of the program presented include the ease of extensibility and a high variability in trading strategies setting.
|
|
|
EASIMEN - Sandbox pro umělé bytosti v simulovaném prostředí
Hencz, Attila ; Neruda, Roman (advisor) ; Pilát, Martin (referee)
Title: EASIMEN - A sandbox for artificial creatures in simulated envi- ronment Author: Attila Hencz Department / Institute: Department of Theoretical Computer Sci- ence and Mathematical Logic Supervisor of the bachelor thesis: Mgr. Roman Neruda, CSc., Insti- tute of Computer Science of the ASCR,1 v.v.i.2 Supervisor's e-mail address: Roman.Neruda@mff.cuni.cz Abstract: The present work investigates the creation of a flexible near- universal simulation environment for artificial intelligence with embodi- ment and real-time simulation in mind. Also, a look is taken at the prob- lems associated with the functioning of such a systems and the methods that can be used in a simulation of this kind. The current implementation of the simulation environment (EASIMEN) is rather simplified and its purpose is the demonstration of the proposed design and architecture. Additionally, there are a couple of simplistic module implementations available for the underlying artificial intelligence architecture proposed by the author (BIAR). These modules are only mere showcases of certain aspects of the issues at hand, and serve as templates for the implemen- tation of more sophisticated modules in the future. Keywords: artificial intelligence, real-time simulation, 3D graphics, phys- ically simulated virtual environment, embodied...
|
|
|
Reducing Complexity of AI in Open-World Games by Combining Search-based and Reactive Techniques
Černý, Martin ; Brom, Cyril (advisor) ; Dignum, Frank (referee) ; Pilát, Martin (referee)
Open-world computer games present the players with a large degree of freedom to interact with the virtual environment. The increased player freedom makes open-world games a challenging domain for artificial intelligence. In this thesis we present three novel techniques to handle various types of complexity inherent in developing artificial intelligence for open-world games. We developed behavior objects that extend the well-known concept of smart objects and help in structuring codebase for reactive reasoning, we propose and implement constraint satisfaction techniques to specify behavior from a global viewpoint and we have shown how adversarial search techniques can mitigate the need for complex reactive decision mechanisms when a large number of parameters has to be taken into account. The general techniques are implemented and evaluated in the context of a complete open-world game Kingdom Come: Deliverance. Powered by TCPDF (www.tcpdf.org)
|
|
|
Mining and management of data on conferences and workshops
Pilát, Martin ; Žemlička, Michal (advisor) ; Eckhardt, Alan (referee)
The goal of this work is to create an application, which would help its users to be acquianted with huge amounts of information on conferences, workshops, congresses, and Symposiums. The number of shown events can be reduced by the use of an advanced system of user-defined filters. The application contains a sophisticated system of user privileges and provides support for creating personal and group calendars. An important part of the application is a module for automated retrieving of information from incoming e-mail messages. This module uses a simple pattern matching for extracting deadlines, topics, name, and other important data on a particular conference. These patterns are stored in a hand-crafted dictionary. The accuracy of this module is about 80% for mining the dates and about 70% for mining other types of data.
|
|
|
Evolutionary Algorithms for Multiobjective Optimization
Pilát, Martin ; Neruda, Roman (advisor) ; Schoenauer, Marc (referee) ; Pošík, Petr (referee)
Multi-objective evolutionary algorithms have gained a lot of atten- tion in the recent years. They have proven to be among the best multi-objective optimizers and have been used in many industrial ap- plications. However, their usability is hindered by the large number of evaluations of the objective functions they require. These can be expensive when solving practical tasks. In order to reduce the num- ber of objective function evaluations, surrogate models can be used. These are a simple and fast approximations of the real objectives. In this work we present the results of research made between the years 2009 and 2013. We present a multi-objective evolutionary algo- rithm with aggregate surrogate model, its newer version, which also uses a surrogate model for the pre-selection of individuals. In the next part we discuss the problem of selection of a particular type of model. We show which characteristics of the various models are im- portant and desirable and provide a framework which combines sur- rogate modeling with meta-learning. Finally, in the last part, we ap- ply multi-objective optimization to the problem of hyper-parameters tuning. We show that additional objectives can make finding of good parameters for classifiers faster. 1
|
|
|
Anomaly Detection Using Generative Adversarial Networks
Měkota, Ondřej ; Fink, Jiří (advisor) ; Pilát, Martin (referee)
Generative adversarial networks (GANs) are able to capture distribution of its inputs. They are thus used to learn the distribution of normal data and then to detect anoma- lies, even if they are very rare; e.g. Schlegl et al. (2017) proposed an anomaly detection method called AnoGAN. However, a major disadvantage of GANs is instability during training. Therefore, Arjovsky et al. (2017) proposed a new version, called Wasserstein GAN (WGAN). The goal of this work is to propose a model, utilizing WGANs, to detect fraudulent credit card transactions. We develop a new method called AnoWGAN+e, partially based on AnoGAN, and compare it with One Class Support Vector Machines (OC-SVM) (Schöl- kopf et al. (2001)), k-Means ensemble (Porwal et al. (2018)) and other methods. Perfor- mance of studied methods is measured by area under precision-recall curve (AUPRC), and precision at different recall levels on credit card fraud dataset (Pozzolo (2015)). AnoW- GAN+e achieved the highest AUPRC and it is 12% better than the next best method OC-SVM. Furthermore, our model has 20% precision at 80% recall, compared to 8% precision of OC-SVM, and 89% precision at 10% recall as opposed to 79% of k-Means ensemble. 1
|
|
|
Evolutionary Algorithms for 2D Cutting Problem
Balcar, Štěpán ; Pilát, Martin (advisor) ; Mareš, Martin (referee)
Creation of optimal cutting plans is an important task in many types of industry. In this work we present a novel evolutionary algorithm designed to deal with this problem. The algorithm assumes rectangular shapes of the objects and creates a cutting plan which is can be cut out using a circular saw. The output is presented in a form usable by automatic saws as well as graphically. The algorithm reduces the amount of the material used and, moreover, also reduces the number of needed employees.
|
|
|
DyBaNeM: Bayesian Model of Episodic Memory
Kadlec, Rudolf ; Brom, Cyril (advisor) ; Lim, Mei Yii (referee) ; Pilát, Martin (referee)
Title: DyBaNeM: Bayesian Model of Episodic Memory Author: Mgr. Rudolf Kadlec E-mail: rudolf.kadlec@gmail.com Department: Department of Software and Computer Science Education Supervisor: Mgr. Cyril Brom, Ph.D. Department of Software and Computer Science Education Abstract: Artificial agents endowed with episodic (or autobiographic) memory systems have the abilities to remember and recall what happened to them in the past. The existing Episodic Memory (EM) models work as mere data-logs with indexes: they enable record, retrieval and delete operations, but rarely organize events in a hierarchical fashion, let alone abstract automatically detailed streams of "what has just happened" to a "gist of the episode." Consequently, the most interest- ing features of human EM, reconstructive memory retrieval, emergence of false memory phenomena, gradual forgetting and predicting surprising situations are out of their reach. In this work we introduce a computational framework for episodic memory modeling called DyBaNeM. DyBaNeM connects episodic mem- ory abilities and activity recognition algorithms and unites these two computer science themes in one framework. This framework can be conceived as a general architecture of episodic memory systems, it capitalizes on Bayesian statistics and, from the psychological...
|
|
|
Time series prediction
Boková, Kateřina ; Pilát, Martin (advisor) ; Koubková, Alena (referee)
In this present work, we provide an overview of methods for time series modelling and prediction. We describe methods based on decomposition as well as methods based on the Box-Jenkins methodology. Moreover, we also discuss methods based on the ideas from computational intelligence -mainly neural networks. Thedescription of the methods is focused on the algorithmic aspects -we derive the ways in which the parameters of the models are set. The work also contains a software, which allows the user to apply the described methods to given time series and compare them among each other.
|
|
|
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.
|
guest ::
RSS feed.