|
|
Convolutional Neural Networks
Lietavcová, Zuzana ; Zbořil, František (referee) ; Zbořil, František (advisor)
This thesis deals with convolutional neural networks. It is a kind of deep neural networks that are presently widely used mainly for image recognition and natural language processing. The thesis describes specifics of convolutional neural networks in comparison with traditional neural networks and is focused on inner computations in the process of learning. Convolutional neural networks typically consist of a different types of layers of neurons and the core part of this thesis is to demonstrate computations of individual types of layers. Learning demonstrating program of a simple convolutional network was designed and implemented using own implementation of neural network. Validity of the implementation was tested by training models for solving a classification task. Experiments with different types of architectures were conducted and their performance was compared.
|
|
|
Coverage-Driven Testing for Multithreaded Programs
Lietavcová, Zuzana ; Šimková, Hana (referee) ; Letko, Zdeněk (advisor)
This work deals with a problem of searching errors in multithreaded programs using a coverage-driven testing technique as perceived in program Maple. The testing consists of two phases. In the first phase of testing a set of coverable behaviours of the tested program is being built. Consequently, the algorithm tries to achieve these behaviours with a help of deterministic test execution. The main acquisition of the work lays in a compact description of Maple including all the technical details. Based on the study of the tool there were weak places identified. Some of them are studied in detail, especially those which use random decision making and prioritizing of the forced behaviours. The result are several modifications of Maple, from which some lead to a higher number of exposed behaviours and higher error exposition in some cases. This is demonstrated on a test suite of parallel programs.
|
|
|
Convolutional Neural Networks
Lietavcová, Zuzana ; Zbořil, František (referee) ; Zbořil, František (advisor)
This thesis deals with convolutional neural networks. It is a kind of deep neural networks that are presently widely used mainly for image recognition and natural language processing. The thesis describes specifics of convolutional neural networks in comparison with traditional neural networks and is focused on inner computations in the process of learning. Convolutional neural networks typically consist of a different types of layers of neurons and the core part of this thesis is to demonstrate computations of individual types of layers. Learning demonstrating program of a simple convolutional network was designed and implemented using own implementation of neural network. Validity of the implementation was tested by training models for solving a classification task. Experiments with different types of architectures were conducted and their performance was compared.
|
|
|
Coverage-Driven Testing for Multithreaded Programs
Lietavcová, Zuzana ; Šimková, Hana (referee) ; Letko, Zdeněk (advisor)
This work deals with a problem of searching errors in multithreaded programs using a coverage-driven testing technique as perceived in program Maple. The testing consists of two phases. In the first phase of testing a set of coverable behaviours of the tested program is being built. Consequently, the algorithm tries to achieve these behaviours with a help of deterministic test execution. The main acquisition of the work lays in a compact description of Maple including all the technical details. Based on the study of the tool there were weak places identified. Some of them are studied in detail, especially those which use random decision making and prioritizing of the forced behaviours. The result are several modifications of Maple, from which some lead to a higher number of exposed behaviours and higher error exposition in some cases. This is demonstrated on a test suite of parallel programs.
|
guest ::
