|
|
Playing Games Using Neural Networks
Buchal, Petr ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this bachelor thesis is to teach a neural network solving classic control theory problems and playing the turn-based game 2048 and several Atari games. It is about the process of the reinforcement learning. I used the Deep Q-learning reinforcement learning algorithm which uses a neural networks. In order to improve a learning efficiency, I enriched the algorithm with several improvements. The enhancements include the addition of a target network, DDQN, dueling neural network architecture and priority experience replay memory. The experiments with classic control theory problems found out that the learning efficiency is most increased by adding a target network. In the game environments, the Deep Q-learning has achieved several times better results than a random player. The results and their analysis can be used for an insight to reinforcement learning algorithms using neural networks and to improve the used techniques.
|
|
|
Overview of Actual Approaches to Classifications
Brezánský, Tomáš ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
This bachelor thesis deals with an overview of current approaches to classifications. It describes various approaches to classifications and their algorithms, focuses on neural networks, Bayesian classifiers and decision trees. The main task of this work is to perform experiments with three classification algorithms, namely, the ID3 algorithm, the RCE neural network and the naive Bayesian classifier. The work contains experiments with given algorithms and evaluates the obtained results.
|
|
|
Description of Relation between Flow and Suspended Sediment Load in a Hydromertic Profiles of a Selected Rivers
Bobková, Dominika ; Janál,, Petr (referee) ; Marton, Daniel (advisor)
The issue of the relationship between water discharge and the suspended sediment loads is a globally highly addressed topic. Knowing the suspended sediment loads in the streams avoids problems with over-filling of water cannons and thus prevents insufficient capacity of water reservoirs. This thesis is partly a follow-up to the bachelor thesis, which extends and introduces new procedures. Neural networks, more specifically multilayer perceptron neural networks, are used to analyse the relationship between water discharge and suspended sediment loads. The results of the networks are then processed in Excel into graphs and evaluated using the coefficient of determination, Nash-Sutcliffe coefficient and RMSE coefficient. The practical application is solved on two profiles - the profile Podhradí nad Dyjí and the profile Židlochovice. Each profile is examined in a different period.
|
|
|
Classification of the vascular tree in fundus images
Tebenkova, Iuliia ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
Retinal image analysis plays a very important role, as human gets around 90% of environment information with the help of eyes. Automation of process of retinal image analysis promotes to improve the efficiency of retinal medical examinations. The following thesis is dedicated to automatic classification methods of retinal vascular system images obtained from a digital fundus camera. Vessel classification method using classifier on the base of neural networks, which is trained and then tested on the retinal vessel segments, is investigated and implemented. In this thesis anatomical retinal survey, properties of image data from digital fundus camera and retinal image classification methods are briefly described. The last chapter is devoted to the evaluation of efficiency of retinal vessel classification with automatic methods.
|
|
|
Recognizing Faces within Image
Svoboda, Pavel ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
The essence of face recognition within the image is generally computer vision, which provides methods and algorithms for the implementation. Some of them are described just in this work. Whole process is split in to three main phases. These are detection, aligning of detected faces and finally its recognition. Algorithms which are used to applied in given issue and which are still in progress from todays view are mentioned in every phase. Implementation is build up on three main algorithms, AdaBoost to obtain the classifier for detection, method of aligning face by principal features and method of Eigenfaces for recognizing. There are theoretically described except already mentioned algorithms neural networks for detection, ASM - Active Shape Models algorithm for aligning and AAM - Active Appearance Model for recognition. In the end there are tables of data retrieved by implemented system, which evaluated the main implementation.
|
|
|
Vehicle Control via Reinforcement Learning
Maslowski, Petr ; Uhlíř, Václav (referee) ; Šůstek, Martin (advisor)
The goal of this thesis is a creation of an autonomous agent that can control a vehicle. The agent utilizes reinforcement learning that uses neural networks. The agent interprets images from the front vehicle camera and selects appropriate actions to control the vehicle. I designed and created reward functions and then experimented with hyperparameters setup. Trained agent simulate driving on the road. The result of this thesis shows a possible approach to control an autonomous vehicle agent using machine learning method in CARLA simulator.
|
|
|
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.
|
|
|
Facial image restoration
Bako, Matúš ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
In this thesis, I tackle the problem of facial image super-resolution using convolutional neural networks with focus on preserving identity. I propose a method consisting of DPNet architecture and training algorithm based on state-of-the-art super-resolution solutions. The model of DPNet architecture is trained on Flickr-Faces-HQ dataset, where I achieve SSIM value 0.856 while expanding the image to four times the size. Residual channel attention network, which is one of the best and latest architectures, achieves SSIM value 0.858. While training models using adversarial loss, I encountered problems with artifacts. I experiment with various methods trying to remove appearing artefacts, which weren't successful so far. To compare quality assessment with human perception, I acquired image sequences sorted by percieved quality. Results show, that quality of proposed neural network trained using absolute loss approaches state-of-the-art methods.
|
|
|
Enhancement of image quality for security forces
Varga, Adam ; Galáž, Zoltán (referee) ; Burget, Radim (advisor)
This bachelor thesis deals with image quality enhancement for security forces. Image quality enhancement in this case means increasing the resolution of image data by using super-resolution techniques using models of deep convolutional neural networks. The thesis in its theoretical part describes the principles of the operation of this technique and in its practical part is presented the work with selected state-of-the-art models in the area of super-resolution.
|
|
|
Sign language detection methods - review
Petr, Luboš ; Venglář, Vojtěch (referee) ; Krejsa, Jiří (advisor)
The Aim of this work is to describe various methods of sign language detection. The output of individual methods is a functional translation of sign language into text in real time. In addition to glove and kinect detection, this work deals with the possibilities of sign language detection from image recording, which is the most prospective method of detection in the future. The thesis is also focused on sign classification using neural networks.
|
guest ::
