|
| |
|
|
Evolutionary Design of Image Classifier
Koči, Martin ; Bidlo, Michal (referee) ; Drahošová, Michaela (advisor)
This thesis deals with evolutionary design of image classifier with help of genetic programming, specifically with cartesian genetic programming. Thesis discribes teoretical basics of machine learing, evolutionary algorithms and genetic programming. Part of this thesis is described design of the program and its implementation. Futhermore, experiments are performed on two solved tasks for the classification of handwritten digits and the classification of cube drawings, which can be used to determine the rate of dementia in Parkinson's disease. The best designed solution for digits is with AUC of 0.95 and for cubes 0.86. Designed solutions are compared by other methods, namely convolutional neural networks (CNN) and the support vector machines (SVM). The resulting AUC for the classification of digits for both CNN and SVM is 0.99, for cubes CNN has a final AUC 0.81 and SVM 0.69. The cubes are then compared with existing solution, which resulted in AUC 0.70, so that the results of the experiments show an improvement in the method used in this thesis.
|
|
|
Algorithms for advance production planning and scheduling
Kršák, Pavol ; Kaczmarczyk, Václav (referee) ; Pásek, Jan (advisor)
Bachelor‘s thesis analyzes solution of operational problems of production planning. Pur- pose of the thesis is presentation of operational problems of production planning and following proposal and implementation of planning algorithms in language C# on specific planning problem. By the presentation of the problematic is listed company „COMPAS automatizace s.r.o.”, which enabled implementation of the project. The thesis analyzes planning methods and process of their implementation. More specifically the thesis ana- lyzes evolutionary algorithms, expert systems in planning and deterministic planning via linear programming. In third chapter is described in more details planning program of production of coffee blends, which was provided by COMPAS company. Like a next, the thesis describes specifically proposal of solving based on evolutionary principle. The solving consists of the model of technology designed to production of coffee blends and ActionList. ActionList represents a set of rules that are governed by model. Then ru- les are defined undergone an evolutionary process in an effort to find better solution the existing. Applied features implemented in the system COMES to repurpose by the imple- mentation of module COMES Modeller are developed together with detailed description in the fourth chapter.
|
|
|
Evolutionary Algorithms in Convolutional Neural Network Design
Badáň, Filip ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
This work focuses on automatization of neural network design via the so-called neuroevolution, which employs evolutionary algorithms to construct artificial neural networks or optimise their parameters. The goal of the project is to design and implement an evolutionary algorithm which can be used in the process of designing and optimizing topologies of convolutional neural networks. The effectiveness of the proposed framework was experimentally evaluated on tasks of image classification on datasets MNIST and CIFAR10 and compared with relevant solutions. The results showed that neuroevolution has a potential to successfully find accurate and effective convolutional neural network architectures.
|
|
|
Software for Biometric Recognition of a Human Eye Iris
Maruniak, Lukáš ; Orság, Filip (referee) ; Drahanský, Martin (advisor)
In my thesis, I focus on the task of recognizing human iris from an image.In the beginning, the work deals with a question of biometrics, its importance and basic concepts, which are necessary for use in following text. Subsequently process of human Iris detection is described together with theory of evolution algorithms. In the implementation part, is described the design of implemented solution, which uses evolution algorithms, where is emphasis on correct pupil and iris boundary detection.
|
|
|
Evolutionary Design of Convolutional Neural Networks
Pristaš, Ján ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
The aim of this Master's thesis is to describe basic technics of evolutionary computing, convolutional neural networks (CNN), and automated design of neural networks using neuroevolution ( NAS - Neural Architecture Search ). NAS techniques are currently being researched more and more, as they speed up and simplify the lengthy and complicated process of designing artificial neural networks. These techniques are also able to search for unconventional architectures that would not be found by classic methods. The work also contains the design and implementation of software capable of automated development of convolutional neural networks using the open-source library TensorFlow. The program uses a multiobjective NSGA-II algorithm for designing accurate and compact CNNs.
|
|
|
Evolution of Complex Behavior in Cellular Automata
Kontra, Matúš ; Vašíček, Zdeněk (referee) ; Bidlo, Michal (advisor)
Celular automata are one of many alternative models of computation. Massive parallelism and the posibillity to describe their local behaviour in a simple way are of particular interest. This thesis describes a different way of representing the local transfer function of cellular automata, which is particulary suitable for use in genetic algorithm. This representation is based on simple model, mirroring the way instruction based register machines operate. The aim of this publication is to analyze and assess applicability of proposed method.
|
|
|
Evolutionary Algorithms in the Task of Boolean Satisfiability
Serédi, Silvester ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
The goal of this Master's Thesis is finding a SAT solving heuristic by the application of an evolutionary algorithm. This thesis surveys various approaches used in SAT solving and some variants of evolutionary algorithms that are relevant to this topic. Afterwards the implementation of a linear genetic programming system that searches for a suitable heuristic for SAT problem instances is described, together with the implementation of a custom SAT solver which expoloits the output of the genetic program. Finally, the achieved results are summarized.
|
|
|
Evolutionary Design of Image Classifier
Koči, Martin ; Bidlo, Michal (referee) ; Drahošová, Michaela (advisor)
This thesis deals with evolutionary design of image classifier with help of genetic programming, specifically with cartesian genetic programming. Thesis discribes teoretical basics of machine learing, evolutionary algorithms and genetic programming. Part of this thesis is described design of the program and its implementation. Futhermore, experiments are performed on two solved tasks for the classification of handwritten digits and the classification of cube drawings, which can be used to determine the rate of dementia in Parkinson's disease. The best designed solution for digits is with AUC of 0.95 and for cubes 0.86. Designed solutions are compared by other methods, namely convolutional neural networks (CNN) and the support vector machines (SVM). The resulting AUC for the classification of digits for both CNN and SVM is 0.99, for cubes CNN has a final AUC 0.81 and SVM 0.69. The cubes are then compared with existing solution, which resulted in AUC 0.70, so that the results of the experiments show an improvement in the method used in this thesis.
|
|
|
Evolutionary Design of Convolutional Neural Networks
Pristaš, Ján ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
The aim of this Master's thesis is to describe basic technics of evolutionary computing, convolutional neural networks (CNN), and automated design of neural networks using neuroevolution ( NAS - Neural Architecture Search ). NAS techniques are currently being researched more and more, as they speed up and simplify the lengthy and complicated process of designing artificial neural networks. These techniques are also able to search for unconventional architectures that would not be found by classic methods. The work also contains the design and implementation of software capable of automated development of convolutional neural networks using the open-source library TensorFlow. The program uses a multiobjective NSGA-II algorithm for designing accurate and compact CNNs.
|
guest ::
