Peter Lacko

Learn More
Many of software engineering tools and systems are focused to monitoring source code quality and optimizing software development. Many of them use similar source code metrics to solve different kinds of problems. This inspired us to propose an environment for platform independent code monitoring, which supports employment of multiple software development(More)
Several authors have reported interesting results obtained by using untrained randomly initialized recurrent part of an recurrent neural network (RNN). Instead of long, difficult and often unnecessary adaptation process, dynamics based on fixed point attractors can be rich enough for further exploitation for some tasks. The principle explaining untrained(More)
In this paper, we study an emergence of game strategy in multiagent systems. Symbolic and subsymbolic approaches are compared. Symbolic approach is represented by a backtrack algorithm with specified search depth, whereas the subsymbolic approach is represented by feedforward neural networks that are adapted by reinforcement temporal difference TD(lambda)(More)
Simulation of human behavior in various situations is nowadays heavily used in miscellaneous research fields (e.g. emergency exits design, psychology, riot or humanitarian help simulation). The Holy Grail is to identify key elements of human beings that drive our behavior and be able to sufficiently simulate them and replicate in artificial computer(More)
In this thesis we focused on subsymbolic approach to machine game play problem. We worked on two different methods of learning. Our first goal was to test the ability of common feed-forward neural networks and the mixture of expert topology. We have derived reinforcement learning algorithm for mixture of expert network topol-ogy. This topology is capable to(More)
  • Peter Lacko
  • 2017
Deep neural networks are intensively researched field of artificial intelligence. Big companies like Google, Microsoft, Baidu or Facebook are supporting research and development in this field. The recent victory over human player in the game of Go points to a huge potential of this approach. Machine learning approaches based on deep learning techniques(More)
The paper proposes an approach for predicting application upgrade time that is being upgraded from one version to another. The focus is primarily concentrated on applications with upgrades consisting mainly of upgrading the relational database. Chosen application databases have the same schema but the content of tables varies. Data from the upgrades are(More)