|
|
Solving Optimization Tasks by ACO Algorithms
Habrnál, Matěj ; Samek, Jan (referee) ; Zbořil, František (advisor)
The presented thesis puts its main focus on the basic optimization algorithms ACO (Ant Colony Optimization) and their development and seeks the inspiration in the ants live. The aim is to demonstrate the activity of these algorithms on optimization problems - the traveling salesman problem and the finding food sources problem and optimal routes between an anthill and food. The thesis also describes experiments that try to determine the influence of adjustable parameters of ant algorithms. First, ACO algorithms theory is described followed then by the application of these algorithms on both selected optimization problems. The conclusion sums up experiments analysis with established applications and evaluating prospective results.
|
|
|
Deep Neural Networks
Habrnál, Matěj ; Zbořil, František (referee) ; Zbořil, František (advisor)
The thesis addresses the topic of Deep Neural Networks, in particular the methods regar- ding the field of Deep Learning, which is used to initialize the weight and learning process s itself within Deep Neural Networks. The focus is also put to the basic theory of the classical Neural Networks, which is important to comprehensive understanding of the issue. The aim of this work is to determine the optimal set of optional parameters of the algori- thms on various complexity levels of image recognition tasks through experimenting with created application applying Deep Neural Networks. Furthermore, evaluation and analysis of the results and lessons learned from the experimentation with classical and Deep Neural Networks are integrated in the thesis.
|
|
|
Solving Optimization Tasks by ACO Algorithms
Habrnál, Matěj ; Samek, Jan (referee) ; Zbořil, František (advisor)
The presented thesis puts its main focus on the basic optimization algorithms ACO (Ant Colony Optimization) and their development and seeks the inspiration in the ants live. The aim is to demonstrate the activity of these algorithms on optimization problems - the traveling salesman problem and the finding food sources problem and optimal routes between an anthill and food. The thesis also describes experiments that try to determine the influence of adjustable parameters of ant algorithms. First, ACO algorithms theory is described followed then by the application of these algorithms on both selected optimization problems. The conclusion sums up experiments analysis with established applications and evaluating prospective results.
|
|
|
Deep Neural Networks
Habrnál, Matěj ; Zbořil, František (referee) ; Zbořil, František (advisor)
The thesis addresses the topic of Deep Neural Networks, in particular the methods regar- ding the field of Deep Learning, which is used to initialize the weight and learning process s itself within Deep Neural Networks. The focus is also put to the basic theory of the classical Neural Networks, which is important to comprehensive understanding of the issue. The aim of this work is to determine the optimal set of optional parameters of the algori- thms on various complexity levels of image recognition tasks through experimenting with created application applying Deep Neural Networks. Furthermore, evaluation and analysis of the results and lessons learned from the experimentation with classical and Deep Neural Networks are integrated in the thesis.
|
guest ::
RSS feed.