National Repository of Grey Literature 9 records found  Search took 0.00 seconds. 
Echo state networks and their application in time series prediction
Savčinský, Richard ; Mráz, František (advisor) ; Matzner, Filip (referee)
Recurrent neural networks (RNN) enable to model dynamical sys- tems with variable input length. Their disadvantage is in inherently difficult trai- ning which means adjusting weights of connections between neurons connected in the network. Echo state networks (ESN) are a special type of RNN which are by contrast trainable rather simply. They include a reservoir of neurons whose state reflect the history of all signals in the network and that is why this type of network is suitable for simulation and prediction of time series. To maximize the computational power of ESN, very precise adjusting and experimenting are required. Because of that, we have created a tool for building and testing such networks. We have implemented a time series forecasting task for the purpose of examination of our tool. We have focused on stock price prediction, which repre- sents an uncertain and complicated area for achieving precise results in. We have compared our tool to other tools and it was comparably successful. 1
Echo state networks and their application in time series prediction
Savčinský, Richard ; Mráz, František (advisor) ; Matzner, Filip (referee)
Recurrent neural networks (RNN) enable to model dynamical sys- tems with variable input length. Their disadvantage is in inherently difficult trai- ning which means adjusting weights of connections between neurons connected in the network. Echo state networks (ESN) are a special type of RNN which are by contrast trainable rather simply. They include a reservoir of neurons whose state reflect the history of all signals in the network and that is why this type of network is suitable for simulation and prediction of time series. To maximize the computational power of ESN, very precise adjusting and experimenting are required. Because of that, we have created a tool for building and testing such networks. We have implemented a time series forecasting task for the purpose of examination of our tool. We have focused on stock price prediction, which repre- sents an uncertain and complicated area for achieving precise results in. We have compared our tool to other tools and it was comparably successful.
Optimization of a circulating multi-car elevator system
Pantůčková, Kristýna ; Fink, Jiří (advisor) ; Matzner, Filip (referee)
Circulating multi-car elevator is a system holding multiple cars in two shafts, where cars move upwards in one shaft and downwards in the other shaft. This system is similar to the paternoster, but cars have to stop on floors and open doors to load and unload passengers. Besides many technical challenges, this sys- tem brings algorithmic problems regarding efficient control of all cars. This thesis studies an off-line optimization problem, where the most efficient elevator system is searched for a fixed set of passengers. For this purpose, we created a computer program, implementing a genetic algorithm for searching for the most efficient elevator control and a discrete event simulation for evaluation of the efficiency of the control. The program provides a graphical user interface for input of parame- ters, generating passengers and displaying the results. 1
Umělý hráč pro Angry Birds
Nikonova, Ekaterina ; Gemrot, Jakub (advisor) ; Matzner, Filip (referee)
Angry Birds is a popular video game, in which the player is provided with a sequence of birds to shoot from a slingshot. The task of the game is to kill all green pigs with maximum possible score. Angry Birds appears to be a difficult task to solve for artificially intelligent agents due to the sequential decision-making, nondeterministic game environment, enormous state and action spaces and requirement to differentiate between multiple birds, their abilities and optimum tapping times. In this thesis, we are presenting several different techniques suitable for the implementation of artificial Angry Birds agent. First, we will show how limited Breath First Search can be used to estimate potentially good shooting points. After that we will discover how reinforcement learning can be applied to the Angry Birds game. Lastly, we will apply Deep reinforcement learning to Angry Birds game by implementing Double Dueling Deep Q- networks. One of our main goals was to build an agent that is able to compete in AIBirds competition and with humans on the game's first 21 levels. In order to do so, we have collected a dataset of game frames that we used to train our agent. We evaluate our agents using results of the previous participants of AIBirds competition and results of volunteer human players.
Creating the Game Strategies for PuppetWars Using Neuroevolution
Šmelko, Adam ; Pilát, Martin (advisor) ; Matzner, Filip (referee)
In recent years the gaming industry has been on increase. In order to maintain competitiveness gaming companies are required to develop more and more compelling computer games what implies the presence of the very responsive artificial intelligence controlling the game elements, on which our work focuses. We have implemented a simple 2D programming game where we have experimented with the artificial intelligence in it trying to create a strategy beeing able to compete with human. We have explored several variations of learning through the evolutionary strategy applied to neural networks and we have created game characters worthy of being an equal opponent to the game user.
Protein secondary structure prediction using deep neural networks
Filippi, Michal ; Hoksza, David (advisor) ; Matzner, Filip (referee)
Determination of protein structure in space is a crucial part of protein function analysis. But structure determination is an expensive and time consuming pro- cess, therefore structure prediction model raised on popularity. The most notable subproblem of protein structure prediction is prediction of local conformation of the adjacent amino acids, ie. secondary structure. This thesis studies usage of deep neural networks for protein secondary structure prediction. We implemented pre- diction model and different modifications are evaluated. Especially compassion of LSTM and GRU memory cells was done. Furthermore, two new preprocessing me- thods are evaluated. Fast PSSM calculation method was proposed and prediction of tertiary structure was used as input for prediction model. Last part of this thesis examine application of filtering methods for models predicting secondary structure with eight classes. 1
Heterogeneous Island Models
Balcar, Štěpán ; Pilát, Martin (advisor) ; Matzner, Filip (referee)
The work deals with heterogeneous island models. The work designs and implements a new island model based on knowledge of homogeneous models of evolutionary algorithms. The model allows dynamic replanning of general computational methods. The work experimentally compares results of homogeneous and heterogeneous models.
Maximizing Computational Power by Neuroevolution
Matzner, Filip ; Mráz, František (advisor) ; Pilát, Martin (referee)
Echo state networks represent a special type of recurrent neural networks. Recent papers stated that the echo state networks maximize their computational performance on the transition between order and chaos, the so-called edge of chaos. This work confirms this statement in a comprehensive set of experiments. Afterwards, the best performing echo state network is compared to a network evolved via neuroevolution. The evolved network outperforms the best echo state network, however, the evolution consumes significant computational resources. By combining the best of both worlds, the simplicity of echo state networks and the performance of evolved networks, a new model called locally connected echo state networks is proposed. The results of this thesis may have an impact on future designs of echo state networks and efficiency of their implementation. Furthermore, the findings may improve the understanding of biological brain tissue. 1
Tracking of 3D Movement
Matzner, Filip ; Barták, Roman (advisor) ; Obdržálek, David (referee)
In this thesis, we propose and evaluate a method for tracking short-term move- ment and orientation of a device using only its on-board sensors - accelerometer, gyroscope and magnetometer. A straightforward method of motion tracking is described from the theoretical perspective and afterwards transformed into a practical algorithm. To improve its performance, we enhance the method with a stabilization system, which corrects the bias caused by sensor inaccuracies every time the device stands still. The effectiveness of the proposed method and the merits of the enhancement are evaluated in several experiments with two mo- bile devices. Furthermore, a complete software solution is included, which allows experimentation with smartphone sensors in a user friendly interface. 1

Interested in being notified about new results for this query?
Subscribe to the RSS feed.