|
|
Neural Networks and Their Applications
Chaloupka, David ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
The aim of this thesis is to present a consistent insight into the most frequently used types of artificial neural networks and their applications. It depicts feedforward neural networks with backpropagation training algorithm, Hopfield networks and self-organizing maps (Kohonen maps). Second part of this thesis demonstrates typical applications of described networks and discusses various factors, which influence performance of these networks on chosen tasks.
|
|
|
Neural Networks for Protein Structure Predictions
Šamšula, Radek ; Bartík, Vladimír (referee) ; Burget, Radek (advisor)
Bachelor's thesis studies the problems of neural networks and prediction of protein secondary structure. This thesis is focused on multilayer neural network with back-propagation learning algorithm and their use for prediction. It describes the infuence of network architecture and their parameters settings on the prediction results. Furthermore suitability of the network for this kind of prediction is discused.
|
|
|
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.
|
|
|
Recurrent Neural Networks in Computer Vision
Křepský, Jan ; Řezníček, Ivo (referee) ; Španěl, Michal (advisor)
The thesis concentrates on using recurrent neural networks in computer vision. The theoretical part describes the basic knowledge about artificial neural networks with focus on a recurrent architecture. There are presented some of possible applications of the recurrent neural networks which could be used for a solution of real problems. The practical part concentrates on face recognition from an image sequence using the Elman simple recurrent network. For training there are used the backpropagation and backpropagation through time algorithms.
|
|
|
Software Library for Artificial Neural Networks with Acceleration Using GPU
Trnkóci, Andrej ; Samek, Jan (referee) ; Zbořil, František (advisor)
Artificial neural networks are demanding to computational power of a computer. Increasing their learning speed could mean new posibilities for research or aplication of the algorithm. And that is a purpose of this thesis. The usage of graphics processing units for neural networks learning is one way how to achieve above mentioned goals. This thesis is offering a survey of theoretical background and consequently implementation of a software library for neural networks learning with a Backpropagation algorithm with a support of acceleration on graphics processing unit.
|
|
|
Coevolution of Cartesian Genetic Algorithms and Neural Networks
Kolář, Adam ; Král, Jiří (referee) ; Zbořil, František (advisor)
The aim of the thesis is to verify synergy of genetic programming and neural networks. Solution is provided by set of experiments with implemented library built upon benchmark tasks. I've done experiments with directly and also indirectly encoded neural netwrok. I focused on finding robust solutions and the best calculation of configurations, overfitting detection and advanced stimulations of solution with fitness function. Generally better solutions were found using lower values of parameters n_c and n_r. These solutions tended less to be overfitted. I was able to evolve neurocontroller eliminating oscilations in pole balancing problem. In cancer detection problem, precision of provided solution was over 98%, which overcame compared techniques. I succeeded also in designing of maze model, where agent was able to perform multistep tasks.
|
|
|
Neural-Fuzzy Systems
Dalecký, Štěpán ; Samek, Jan (referee) ; Zbořil, František (advisor)
The thesis deals with artificial neural networks theory. Subsequently, fuzzy sets are being described and fuzzy logic is explained. The hybrid neuro-fuzzy system stemming from ANFIS system is designed on the basis of artificial neural networks, fuzzy sets and fuzzy logic. The upper-mentioned systems' functionality has been demonstrated on an inverted pendulum controlling problem. The three controllers have been designed for the controlling needs - the first one is on the basis of artificial neural networks, the second is a fuzzy one, and the third is based on ANFIS system. The thesis is aimed at comparing the described systems, which the controllers have been designed on the basis of, and evaluating the hybrid neuro-fuzzy system ANFIS contribution in comparison with particular theory solutions. Finally, some experiments with the systems are demonstrated and findings are assessed.
|
|
| |
|
|
The Betting Agent
Bělohlávek, Jiří ; Rozman, Jaroslav (referee) ; Grulich, Lukáš (advisor)
This master thesis deals with design and implementation of betting agent. It covers issues such as theoretical background of an online betting, probability and statistics. In its first part it is focused on data mining and explains the principle of knowledge mining form data warehouses and certain methods suitable for different types of tasks. Second, it is concerned with neural networks and algorithm of back-propagation. All the findings are demonstrated on and supported by graphs and histograms of data analysis, made via SAS Enterprise Miner program. In conclusion, the thesis summarizes all the results and offers specific methods of extension of the agent.
|
|
|
Creation of Unit for Datamining
Krásenský, David ; Burgetová, Ivana (referee) ; Lukáš, Roman (advisor)
The goal of this work is to create data mining module for information system Belinda. Data from database of clients will be analyzed using SAS Enterprise Miner. Results acquired using several data mining methods will be compared. During the second phase selected data mining method will be implemented such as module of information system Belinda. The final part of this work is evaluation of acquired results and possibility of using this module.
|
guest ::
