|
|
Design of signals for nonlinear system modeling
Kuba, Michael ; Ištvánek, Matěj (referee) ; Miklánek, Štěpán (advisor)
This Master’s thesis is focused on training signals for nonlinear system modeling using deep learning. A theoretical introduction to the problem is described, including an initial description of signals and nonlinear distortion audio effects. The goal of the thesis is to design a set of artificial training signals for creating models of distortion guitar effects or tube guitar amplifiers. The designed set of artificial training signals is then processed, utilizing guitar and bass guitar effects, and using a recurrent neural network their models are trained. The quality of the resulting models is afterwards compared with the quality of the models trained with the help of a reference training signal, composed of electric guitar recordings, and signals from commercially available devices. The comparison is carried out in accordance to objective metrics and with subjective evaluation by the MUSHRA listening test.
|
|
|
Neural networks used in autonomous vehicles
Ryšavý, Jan ; Píštěk, Václav (referee) ; Kučera, Pavel (advisor)
This bachelor thesis deals with the use of neural networks in autonomous vehicles. The first part of the thesis presents the basic principles of neural networks and learning methods that are used in autonomous vehicles. Then the thesis describes the architecture and functions of neural networks. The second part of the thesis also describes the different types of autonomous vehicles, their classifications and an overview of the sensors used by autonomous vehicles. The last part of the thesis deals with the implementation of neural networks in ECUs using programming languages and libraries, and applications such as object detection and marker recognition.
|
|
|
Advanced sleep quality estimation
Benáček, Petr ; Ředina, Richard (referee) ; Filipenská, Marina (advisor)
This thesis deals with the assessment of sleep quality using modern deep learning methods. The thesis describes metrics for automatic classification of sleep stages. A selected database of sleep data is discussed. Due to the low number of data in the wakefulness phase, different methods of data augmentation are described and implemented. Models based on 1D convolutional networks are the basis for the classification. As a result, models for binary classification and classification of 3 and 4 sleep phases are prepared. Finally, sleep quality metrics are calculated using these models and the results are compared with the literature.
|
|
|
Multilayer neural network
Kačer, Petr ; Klusáček, Jan (referee) ; Jirsík, Václav (advisor)
Bachelor's thesis describes the basics of issue of multilayer neural networks and explains principle of backpropagation algorithm. Next part of thesis is about development of a software for learning and testing multilayer neural networks and describes its graphical user interface. Last part of thesis is dedicated to tutorial examples and practical demonstrations of multilayer neural network usage.
|
|
| |
|
|
The GPU Based Acceleration of Neural Networks
Šimíček, Ondřej ; Jaroš, Jiří (referee) ; Petrlík, Jiří (advisor)
The thesis deals with the acceleration of backpropagation neural networks using graphics chips. To solve this problem it was used the OpenCL technology that allows work with graphics chips from different manufacturers. The main goal was to accelerate the time-consuming learning process and classification process. The acceleration was achieved by training a large amount of neural networks simultaneously. The speed gain was used to find the best settings and topology of neural network for a given task using genetic algorithm.
|
|
|
Scene Analysis Based on the 2D Images
Hejtmánek, Martin ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
This thesis deals with an object surface analysis in a simple scene represented by two-dimensional raster image. It summarizes the most common methods used within this branch of information technology and explains both their advantages and drawbacks. It introduces the design of an surface profile analysis algorithm based on the lighting analysis using knowledge and experiences from previous work. It contains a detailed description of the implemented algorithm and discusses the experimental results. It also brings up options for the possible enhancement of the projected algorithm.
|
|
|
Building deep networks using autoencoders
Lohniský, Michal ; Veselý, Karel (referee) ; Hradiš, Michal (advisor)
This thesis deals with pretraining deep networks by autoencoders. Components of neural networks are described in first chapters. Rest of chapters aims to deep network trainings and to results of experiments where autoencoder pretraining and Backpropagation algorithm are compared. Results showed positive contribution of autoencoder pretraining, mainly in combination with Finetuning.
|
|
|
Adaptive controllers with principles of artificial intelligence and its comparison with classical identifications methods
Vaňková, Tereza ; Dokoupil, Jakub (referee) ; Pivoňka, Petr (advisor)
Master’s thesis is focused on the adaptive controllers. The first theoretic part mainly describes the parametric identification, which belongs to the most important part of the adaptive controller’s structure. Classical identification methods (the recursive least squares methods) are firstly mentioned and afterwards the identification methods based on the neural network (the Marquardt-Levenberg algorithm and the new identification algorithm NIA inspired by the neural networks) are described. At the conclusion of the theoretic part there are mentioned the algorithm of the adaptive controller’s tuning which uses the identification parameters (the modified Z-N method) and the tested types of adaptive controllers. Particular results, which were found out by verifying of the adaptive controllers on the simulation and real models, are contained in second, the practical, part of the thesis. Finally, achieved results are compared with the classical discrete PID controller and with the adaptive controller of the B&R company.
|
|
|
Chatbot Based on Artificial Neural Networks
Červíček, Petr ; Novotný, Ondřej (referee) ; Szőke, Igor (advisor)
The thesis pursues the implementation of the chatbot based on neural networks. It uses Long short term memory networks, which remember long-term dependencies. Chatbot was implemented in Python with superstructure Keras and is based on sequence-to-sequence. Chatbot was also tested by BLEU and given to users, who chatted with the chatbot. For a better understanding of the given problematics, there is simple description of the chatbot history and used technologies.
|
guest ::
