|
|
Symbolic Regression and Coevolution
Drahošová, Michaela ; Žaloudek, Luděk (referee) ; Sekanina, Lukáš (advisor)
Symbolic regression is the problem of identifying the mathematic description of a hidden system from experimental data. Symbolic regression is closely related to general machine learning. This work deals with symbolic regression and its solution based on the principle of genetic programming and coevolution. Genetic programming is the evolution based machine learning method, which automaticaly generates whole programs in the given programming language. Coevolution of fitness predictors is the optimalization method of the fitness modelling that reduces the fitness evaluation cost and frequency, while maintainig evolutionary progress. This work deals with concept and implementation of the solution of symbolic regression using coevolution of fitness predictors, and its comparison to a solution without coevolution. Experiments were performed using cartesian genetic programming.
|
|
|
Coevolutionary Algorithm in FPGA
Hrbáček, Radek ; Vašíček, Zdeněk (referee) ; Drahošová, Michaela (advisor)
This thesis deals with the design of a hardware acceleration unit for digital image filter design using coevolutionary algorithms. The first part introduces reconfigurable logic device technology that the acceleration unit is based on. The theoretical part also briefly characterizes evolutionary and coevolutionary algorithms, their principles and applications. Traditional image filter designs are compared with the biologically inspired design methods. The hardware unit presented in this thesis exploits dual MicroBlaze system extended by custom peripherals to accelerate cartesian genetic programming. The coevolutionary image filter design is accelerated up to 58 times. The hardware platform functionality in the task of impulse noise filter design and edge detector design has been empirically analyzed.
|
|
|
Coevolution in Evolutionary Circuit Design
Veřmiřovský, Jakub ; Hrbáček, Radek (referee) ; Drahošová, Michaela (advisor)
This thesis deals with evolutionary design of the digital circuits performed by a cartesian genetic programing and optimization by a coevolution. Algorithm coevolves fitness predictors that are optimized for a population of candidate digital circuits. The thesis presents theoretical basis, especially genetic programming, coevolution in genetic programming, design of the digital circuits, and deals with possibilities of the utilization of the coevolution in the combinational circuit design. On the basis of this proposal, the application designing and optimizing logical circuits is implemented. Application functionality is verified in the five test tasks. The comparison between Cartesian genetic programming with and without coevolution is considered. Then logical circuits evolved using cartesian genetic programming with and without coevolution is compared with conventional design methods. Evolution using coevolution has reduced the number of evaluation of circuits during evolution in comparison with standard cartesian genetic programming without coevolution and in some cases is found solution with better parameters (i.e. less logical gates or less delay).
|
|
|
Coevolution of Cartesian Genetic Algorithms and Neural Networks
Kolář, Adam ; Král, Jiří (referee) ; Zbořil, František (advisor)
The aim of the thesis is to verify synergy of genetic programming and neural networks. Solution is provided by set of experiments with implemented library built upon benchmark tasks. I've done experiments with directly and also indirectly encoded neural netwrok. I focused on finding robust solutions and the best calculation of configurations, overfitting detection and advanced stimulations of solution with fitness function. Generally better solutions were found using lower values of parameters n_c and n_r. These solutions tended less to be overfitted. I was able to evolve neurocontroller eliminating oscilations in pole balancing problem. In cancer detection problem, precision of provided solution was over 98%, which overcame compared techniques. I succeeded also in designing of maze model, where agent was able to perform multistep tasks.
|
|
|
Image Classification Using Genetic Programming
Jašíčková, Karolína ; Vašíček, Zdeněk (referee) ; Sekanina, Lukáš (advisor)
This thesis deals with image classification based on genetic programming and coevolution. Genetic programming algorithms make generating executable structures possible, which allows us to design solutions in form of programs. Using coevolution with the fitness prediction lowers the amount of time consumed by fitness evaluation and, therefore, also the execution time. The thesis describes a theoretical background of evolutionary algorithms and, in particular, cartesian genetic programming. We also describe coevolutionary algorithms properties and especially the proposed method for the image classifier evolution using coevolution of fitness predictors, where the objective is to find a good compromise between the classification accuracy, design time and classifier complexity. A part of the thesis is implementation of the proposed method, conducting the experiments and comparison of obtained results with other methods.
|
|
|
Allelopathy in constitution of plant communities
Kučera, Pavel ; Weiser, Martin (advisor) ; Hadincová, Věroslava (referee)
Allelopathy, the ability of some plants to decrease the fitness of other plants by secondary metabolites, has been known for a very long time. The scientific community paid great attention to its research. Despite this, there is still a lot of ambiguity surrounding this phenomenon. In the past, the role of allelopathy in the constitution of plant communities had been often overlooked. The situation improved slightly in the past years. Several new articles summarizing information about the ecological aspect of allelopathy have been published. However, there are many unanswered questions about its widespread in plant communities and the degree of its influence on the ecosystem. This bachelor thesis is focused on summarizing contemporary knowledge about the influence of allelopathy, mainly from the ecological viewpoint, and presenting possible directions for future research. There is included a short list of the most common allelochemicals, basic principles of the functioning of allelopathy, its widespread through plant taxa, and its effect on the plant communities, mutualistic microorganisms, and the whole ecosystem. There is also mentioned the role of allelopathy in the process of invasion of alien species and at the end of the thesis, I discussed possible utilization of accumulated information in...
|
|
|
Plant adaptations for pollination by nocturnal animals
Bakovská, Julie ; Tropek, Robert (advisor) ; Sklenář, Petr (referee)
Nocturnal pollination is a part of the reproductive process of plants. The night is characterized by changes in abiotic factors, mainly by a decrease in solar radiation and temperature, while plants and pollinators adapt to these conditions. Plants and pollinators adapt to each other throught the process of coevolution. As a result plants present traits preferred by their pollinators. Sets of convergent traits shared by plants pollinated by single functional group are called pollination syndromes and include reward type, scent, colour and flower morphology. The pollination syndromes and other adaptations of plants pollinated by nocturnal pollinators are presented in this thesis, in the context of adaptations of pollinators' senses to nighttime conditions. Simultaneously, it is referred to the evolutionary reasons for the transition of activity to the night. Significant nocturnal pollinators, associated with pollination syndromes include moths, divided into hawkmoths (sphingophily pollination syndrome) and other nocturnal moths (phalaenophily), bats (chiropterophily) and non-flying mammals (therophily). Other important nocturnal pollinators exhibiting adaptations to nocturnal pollination are beetles and nocturnal bees.
|
|
|
\kur{Apodemus} vs. \kur{Eimeria}: Evolutionary factors of speciation and genomic diversification in host-parasite system
MÁCOVÁ, Anna
This thesis discusses and explains phylogenetic patterns observed in two different organisms: Eimeria, an unicellular parasite, and Apodemus, a rodent that often serves as a host for this parasitic species. The situation in rodents is intuitive, clearly reflecting their biogeographic history. Phylogenetic pattern in A. agrarius corresponds with its spread from the core locality of its distribution eastward. The lack of the genetic variability in European populations hints the recent origin of this population with the low number of founders. The phylogeny of A. flavicollis, a rodent inhabiting almost the whole Europe, reflects the situation during the last glacial maximum (i.e. speciation in several subpopulations that did not interbreed, but retained their independent nature). The situation in Eimeria is more complex. Parasites always fight in "arm races", trying to accommodate to their hosts as best they can, and to avoid their defense. This results in coevolutionary events such as cospeciation, host switches, duplications, and other events that form the genetic variability in parasites. The study of evolutionary relationships in Eimeria may be difficult due to lack or morphological and/or relevant molecular data. This thesis adds more information to this view. Several other studies were also included in this thesis to provide a broader picture of the complexity of host-parasite systems.
|
|
| |
|
|
Population Genetics of Parasites and Their Arthropod Hosts
Bezányiová, Kateřina ; Straka, Jakub (advisor) ; Votýpka, Jan (referee)
Arthropoda are currently the largest metazoan phylum. Given that organisms with parasitic lifestyle are thought to comprise the majority of existing species, it's easy to imagine an immense diversity of parasites interacts with arthropods. However, in comparison to organisms parasitising vertebrates, parasites of arthropods are direly understudied despite their abundance, importance, and potential usefulness. Amongst other things, parasites can be used as tools allowing the inference of information on host life history, ecology, and past events the host species have experienced. Population genetic structure of parasites and other symbionts may reflect these traits and events due to their close relationship with the host. Even though parasites comprise a diverse assemblage of taxa, it's possible to identify convergent patterns in their biology. Models predicting congruent population genetic co- structuring can be thus based on a few traits such as host specificity, life cycle complexity or parasite and/or host dispersal. In some cases, the parasite may provide better resolution of population structure than the host itself, serving as a proxy that may be used to direct conservation programmes of both the host and parasite, as has already been done with parasites of vertebrates. This thesis summarises known...
|
guest ::
