This master thesis describes stochastic optimization algorithms inspired in nature that use population of individuals - evolutionary algorithms. Genetic programming and its variant - cartesian genetic programming is described in a greater detail. This thesis is further focused on the analysis and visualization of digital circuit evolution records. Existing tools for visualization of the circuit evolution were analysed, but because no suitable tool allowing complex analysis of the circuit evolution was found, a new set of functions was proposed and the principles of a new tool were formulated. These functions were implemented in form of an interactive GUI application in Java programming language. The application was described in detail and then used for analysis of digital circuit evolution records.

This thesis deals with the usage of coevolution in the task of symbolic regression. Symbolic regression is used for obtaining mathematical formula which approximates the measured data. It can be executed by genetic programming - a method from the category of evolutionary algorithms that is inspired by natural evolutionary processes. Coevolution works with multiple evolutionary processes that are running simultaneously and influencing each other. This work deals with the design and implementation of the application which performs symbolic regression using coevolution on test-based problems. The test set was generated by a new method, which allows to adjust its size dynamically. Functionality of the application was verified on a set of five test tasks. The results were compared with a coevolution algorithm with a fixed-sized test set. In three cases the new method needed lesser number of generations to find a solution of a desired quality, however, in most cases more data-point evaluations were required.

Master thesis is focused on classification of application protocols based on application data taken from layer L7 of ISO/OSI model. The aim of the thesis is to suggest a classifier for SDM system (Software defined monitoring) so it could be used for links with throughput up to 100 Gb/s. At the same time it should classify with the fewest possible errors.Designed classifier consists of two parts. First part depicts encoders for encoding selected attributes. Second part deals with evaluating circuit which detects series characteristic for particular application protocols on the output from the first part. Considered attributes and series are taken from statistic analyzes of application protocol data.The classifier itself is designed so it can be implemented in FPGA and enables modification set of application protocols who intended for classification. The quality of  designed classifier is tested on real network data. The results of classification are compared with current methods used for classification of application protocols.

This master thesis deals with application of an evolutionary algorithm in the creation of regression tests. In the first section, description of functional verification, verification methodology, regression tests and evolutionary algorithms is provided. In the following section, the evolutionary algorithm, the purpose of which is to achieve reduction of the number of test vectors obtained in the process of functional verification, is proposed. Afterwards, the proposed algorithm is implemented and a set of experiments is evaluated. The results are discussed.

Master's thesis studies the possibilities of generating 3D trees using variety of methods including context-free grammars and L-systems. Master's thesis also includes chapter on evolutionary and genetic algorithms, which briefly summarize their function. In this project genetic algorithm which takes 2D image of tree and the beginning of its trunk is proposed. Based on this information it will generate 3D tree which is visually close to the original image. In addition to methods of generating trees, reader will get information about processing input image and designing test application.

This work deals with evolutionary design of 3D structures. The work brings the summary of the previous works in this area and brings autor's suggested solution of evolutionary design of 3D structures. This paper seeks to the ability of easy fitness function definition in the systems for evolutionary design of structures. The author tries to make one of the first steps to the future systems for evolution design of any universal structures in contrast with the evolution systems for design of a concrete type of structure. The result of this work is the basic system for evolutionary design of 3D structures with the ability of external fitness function definition via the XML file. This paper offers also the  simple advices and observations for the potential future work in this area.

This thesis deals with evolutionary and genetic algorithms and the possible ways of combining them. The theoretical part of the thesis describes genetic algorithms and neural networks. In addition, the possible combinations and existing algorithms are presented. The practical part of this thesis describes the implementation of the algorithm NEAT and the experiments performed. A combination with differential evolution is proposed and tested. Lastly, NEAT is compared to the algorithms backpropagation (for feed-forward neural networks) and backpropagation through time (for recurrent neural networks), which are used for learning neural networks. Comparison is aimed at learning speed, network response quality and their dependence on network size.

The field of FPGA design is ever-growing due to costs being lower than that of ASICs, as well as the time and cost of development. Creating programs to run on them is equally important as developing the devices themselves. Utilizing the increase in performance over software, as well as the ease of reprogramming the device, has led to complex concepts and algorithms that would otherwise be very time-consuming when implemented on software. One such focus has been towards a search and optimization algorithm called the genetic algorithm. The proposed approach is to take an existing application of the genetic algorithm on an FPGA, developed by Fernando et al. [1], and create several instances of it to make a parallel genetic algorithm engine. The genetic algorithm cores are interfaced with a controller module that will control the flow of data between them to implement the parallel execution. Both coarse-grained and fine-grained parallelism are tested and results collected to find the best performance when compared to the single core design. Initial experimental results show some improvement over the number of generations required to reach the optimal fitness level, as well as more significant improvement for the number of generations needed for the average fitness to reach the optimal level.

No description available.

Graphical Processing Units stand for the success of Artificial Neural Networks over the past decade and their broader application in the industry. Another promising field of Artificial Intelligence is Evolutionary Algorithms. Their parallelization ability is well known and has been successfully applied in practice. However, these attempts focused on multi-core and multi-machine parallelization rather than on the GPU. This work explores the possibilities of Evolutionary Algorithms parallelization on GPU. I propose implementation in PyTorch library, allowing to execute EA on both CPU and GPU. The proposed implementation provides the most common evolutionary operators for Genetic Algorithms, Real-Coded Evolutionary Algorithms, and Particle Swarm Op- timization Algorithms. Finally, I show the performance is an order of magnitude faster on GPU for medium and big-sized problems and populations. 1