|
|
Fooling of Algorithms of Computer Vision
Hrabal, Matěj ; Bartl, Vojtěch (referee) ; Herout, Adam (advisor)
The goal of this work was to research existing methods of computer vision and computer recognition fooling. My focus was on group of methods called pixel attacks. Another part of my thesis talks about methods of detecting and fighting against computer vision fooling. Implementation of various pixel attack methods and methods of defending against these kinds of attacks was done using the python programming language and python library Keras. Solution that I have created works as standalone application allowing user to perform various pixel attack methods on chosen image. This tool also allows collection of statistics from performed pixel attacks and is able to detect possible attacks in these images.
|
|
| |
|
|
Evolutionary Algorithms for Neural Networks Learning
Vosol, David ; Rozman, Jaroslav (referee) ; Zbořil, František (advisor)
Main point of this thesis is to find and compare posibilities of cooperation between evolutionary algorithms and neural network learning and their comparison with classical learning technique called backpropagation. This comparison is demonstrated with deep feed-forward neural network which is used for classification tasks. The process of optimalization is via search of optimal values of weights and biases within neural network with fixed topology. We chose three evolutionary approaches. Genetic algorithm, differential evolution and particle swarm optimization algorithm. These three approaches are also compared between each other. The demonstrating program is implemented in Python3 programming language without usage of any third parties libraries focused on deep learning.
|
|
|
Evolutionary Optimization of Control Algorithms
Weisser, Roman ; Šeda, Miloš (referee) ; Zelinka,, Ivan (referee) ; Ošmera, Pavel (advisor)
The dissertation thesis deals with Evolution optimization of control algorithms. The first part of the thesis describes the principles and partial methods of evolution optimization methods especially those used in two-level transplant evolution method. Later the grammatical evolution method is described, which modified algorithm became impulse for creation of transplant evolution method. The transplant evolution method and its two-level modification are new evolutionary algorithms proposed in this work, which were used for optimization of structure and parameters of general controllers control algorithms. The transplant evolution algorithm and its extended two-level modification are described in detail in next chapters. The proper settings of evolutionary algorithms are important for minimization the time of optimization and for finds results approaching the global optimum. For proper setting the parameters of differential evolution was created meta-evolution algorithm that is described in chapter named meta-evolution. The basic concepts of control, chosen methods of system identification and controller parameters settings are described in next part. This part describes algorithms of digital controllers and some specific methods uses in digital control. The demonstrations of control algorithm optimizations of various types of controllers are showed in experimental part. The optimized algorithms of general controllers are compared with various types of PSD controllers which were set by various algebraic methods or differential evolution for various models of systems. In the conclusion of this work is stated a recommendation for further development of evolutionary optimization of controllers are focusing on parallel and distributed computing.
|
|
|
Evolutionary algorithms
Haupt, Daniel ; Polách, Petr (referee) ; Honzík, Petr (advisor)
The first part of this work deals with the optimization and evolutionary algorithms which are used as a tool to solve complex optimization problems. The discussed algorithms are Differential Evolution, Genetic Algorithm, Simulated Annealing and deterministic non-evolutionary algorithm Taboo Search.. Consequently the discussion is held on the issue of testing the optimization algorithms through the use of the test function gallery and comparison solution all algorithms on Travelling salesman problem. In the second part of this work all above mentioned optimization algorithms are tested on 11 test functions and on three models of placement cities in Travelling salesman problem. Firstly, the experiments are carried out with unlimited number of accesses to the fitness function and secondly with limited number of accesses to the fitness function. All the data are processed statistically and graphically.
|
|
|
Optimization of large technology compound design
Krňávek, Ondřej ; Kršík, Jakub (referee) ; Nevařil, Aleš (advisor)
This thesis deals with the optimization of the structural design of large technology compounds. The main emphasis is placed on the participation of available optimization instruments in the design of supporting structures of these constructions. The introductory part is primarily focused on the optimization itself. In this part are further specified also used optimization methods, computational finite element method, implemented code checks and calculation of cost of construction. The main part is dedicated to application of optimization procedure for the design of steel supporting structure of the auxiliary technological object of thermal power plant. The objective criterium shall then constitute the total cost of construction works along with operating costs. For the solution is used Scia Engineer software together with optimization module Scia Engineer Optimization Toolbox. The whole analysis is presented comprehensively from the description of computational model to results evaluation. The attention is paid to the optimization task settings, technical solution of optimization, optimization methods deployment and during the calculation process (especially to the development of objective function values and desing constraints during the optimization solution).
|
|
| |
|
|
Evolutionary Algorithms
Szöllösi, Tomáš ; Mézl, Martin (referee) ; Kozumplík, Jiří (advisor)
The task of this thesis was focused on comparison selected evolutionary algorithms for their success and computing needs. The paper discussed the basic principles and concepts of evolutionary algorithms used for optimization problems. Author programmed selected evolutionary algorithms and subsequently tasted on various test functions with exactly the given input conditions. Finally the algorithms were compared and evaluated the results obtained for different settings.
|
|
|
Evolutionary Design of Quantum Operator
Kraus, Pavel ; Mrázek, Vojtěch (referee) ; Bidlo, Michal (advisor)
The goal of this thesis is to utilize various evolutionary algorithms for quantum operator design in the form of unitary matrices in direct representation. Evolution strategy, differential evolution, Particle Swarm Optimization and artificial bee colony algorithms were chosen. In this thesis, the third and fourth algorithms were used for the first time in relation to quantum operator design. The experiments have shown that the utilization of direct representation gives results of acceptable quality.
|
|
|
Neuroevolution Principles and Applications
Herec, Jan ; Strnadel, Josef (referee) ; Bidlo, Michal (advisor)
The theoretical part of this work deals with evolutionary algorithms (EA), neural networks (NN) and their synthesis in the form of neuroevolution. From a practical point of view, the aim of the work is to show the application of neuroevolution on two different tasks. The first task is the evolutionary design of the convolutional neural network (CNN) architecture that would be able to classify handwritten digits (from the MNIST dataset) with a high accurancy. The second task is the evolutionary optimization of neurocontroller for a simulated Falcon 9 rocket landing. Both tasks are computationally demanding and therefore have been solved on a supercomputer. As a part of the first task, it was possible to design such architectures which, when properly trained, achieve an accuracy of 99.49%. It turned out that it is possible to automate the design of high-quality architectures with the use of neuroevolution. Within the second task, the neuro-controller weights have been optimized so that, for defined initial conditions, the model of the Falcon booster can successfully land. Neuroevolution succeeded in both tasks.
|
guest ::
