This thesis deals with employing coevolutionary principles to the image filter design. Evolutionary algorithms are very advisable method for image filter design. Using coevolution, we can add the processes, which can accelerate the convergence by interactions of candidate filters population with population of fitness predictors. Fitness predictor is a small subset of the training set and it is used to approximate the fitness of the candidate solutions. In this thesis, indirect encoding is used for predictors evolution. This encoding represents a mathematical expression, which selects training vectors for candidate filters fitness prediction. This approach was experimentally evaluated in the task of image filters for various intensity of random impulse and salt and pepper noise design and the design of the edge detectors. It was shown, that this approach leads to adapting the number of target objective vectors for a particular task, which leads to computational complexity reduction.

In recent years, there has been a strong need for the design of integrated  circuits showing low power consumption. It is possible to create intentionally approximate circuits which don't fully implement the specified logic behaviour, but exhibit improvements in term of area, delay and power consumption. These circuits can be used in many error resilient applications, especially in signal and image processing, computer graphics, computer vision and machine learning. This work describes an evolutionary approach to approximate design of arithmetic circuits and other more complex systems. This text presents a parallel calculation of a fitness function. The proposed method accelerated evaluation of 8-bit approximate multiplier 170 times in comparison with the common version. Evolved approximate circuits were used in different types of edge detectors.

The goal of this project is to design a hardware unit that is designed to accelerate evolutionary design of digital circuits on transistor level. The project is divided to two parts. The first one describes design methods of the MOSFET circuits and issues of evolutionary algorithms. It also analyses current results in this domain and provides a new method for the design and optimization. The second part describes proposed unit that accelerates the new method on the circuit Zynq which integrates ARM processor and programmable logic. The new method functionality has been empirically analysed in the task of optimization of few circuits with more inputs. The hardware unit has been tested for designing of gates on transistor level.

This project deals with combinational digital circuits and their optimization. First there are presented main levels of abstraction utilized in the design of combinational digital circuits. Afterwards different methods are surveyed for optimization of combinational digital circuits. The next part of this project is mainly devoted to evolutionary algorithms, their common characteristics and branches: genetic algorithms, evolutionary strategies, evolutionary programming and genetic programming. The variant of genetic programming called Cartesian Genetic Programming (CGP) and the use of CGP in various areas, particularly in the synthesis and optimization of combinational logic circuits are described in detail. The project also discusses some modifications of CGP and the scalability problem of evolutionary circuit design. Consequential part of this thesis describes the method for evolution resynthesis of combinational digital circuits. There is description of design, especially the method of splitting circuits into subcircuits, and implementation details. Finally experiments with these method and their results are described.

The main goal of the master's thesis is to compose a study on cartesian genetic programming with focus on evolution of circuits and to design a concept for visualisation of this evolution. Another goal is to create a program to visualise the circuit evolution in cartesian genetic programming, its generations and chromosomes. The program is capable of visualising the changes between generations and chromosomes and comparing more chromosomes at once. Several user cases had been prepared for the resulting program.

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.

The aim of this thesis is to experimentally evaluate the performance of several distinct representations of transition functions for cellular automata. Cellular automata have many potential applications for simulating various phenomena (e.g. natural processes, physical systems, etc.). Parallel computation of cellular automata is based on local cell interactions. Such computation, however, may prove difficult to program the CA, which is the reason for applying evolutionary techniques for the design of cellular automata in many cases. Evolutionary algorithms, based on Darwin's theory of evolution, have been used to find human-competitive solutions to many problems. In order to perform the evolutionary design of cellular automata, special encodings of the candidate solutions are often necessary. For this purpose the performance testing of various representations of the transition functions will be investigated. In particular, table representation, conditionally matching rules, and genetic programming will be treated. The problem of square calculations in cellular automata will be considered as a case study.

Tato disertační práce se zabývá evolučním návrhem a optimalizací jak běžných, tak polymorfních digitálních obvodů. V práci jsou uvedena a vyhodnocena nová rozšíření kartézského genetického programování (Cartesian Genetic Programming, CGP), která umožňují zkrácení výpočetního času a získávání kompaktnějších obvodů. Další část práce se zaměřuje na nové metody syntézy polymorfních obvodů. Uvedené metody založené na polymorfních binárních rozhodovacích diagramech a polymorfním multiplexovaní rozšiřují běžné reprezentace digitálních obvodů, a to s ohledem na začlenění polymorfních hradel. Z důvodu snížení počtu hradel v obvodech syntetizovaných uvedenými metodami je provedena evoluční optimalizace založená na CGP. Implementované polymorfní obvody, které jsou optimalizovány s využitím CGP, reprezentují nejlepší známá řešení, jestliže je jako cílové kritérium brán počet hradel obvodu.

This master's thesis deals with evolutionary algorithms and how them to use to design of combinational circuits. Genetic programming especially CGP is the most applicable to use for this type of task. Furthermore, it deals with computation on computer cluster and the use of evolutionary algorithms on them. For this computation is the most suited island models with CGP. Then a new way of recombination in CGP is designed to improve them. This design is implemented and tested on the computer cluster.

This essay explores the application of zoomorphism and anthropomorphism in Yann Martel’s novel Life of Pi. The novel, rather than being a mere shipwreck-narrative or a miraculous tale with religious overtones, is also a story about the complicated and perhaps inevitably divided relationship between humans and animals. This essay introduces the fields of ecocriticism and animal studies and defines anthropomorphism and zoomorphism in the context of literary criticism. The essay goes on to discuss the layers of meaning behind the names and naming of the two main characters using Burke’s rhetoric of identification, analyses the anthropomorphism and religiosity in the novel’s two stories, and analyses the two accepted readings of the novel from a zoomorphic perspective. The essay looks at the human-animal divide and its problems in literature, going into Derrida’s animal philosophy to provide a counterpoint to a view derived from Cartesian dualism. In a straight reading of the novel, the first story is regarded as metaphoric while the second story is regarded as literal. There is an alternative reading where it is left to the reader to decide which story is true, but this essay argues that this reading negates a metaphoric interpretation of either story and therefore dismisses the straight reading. Instead, this essay proposes a third, zoomorphic reading, fully compatible with the straight reading, where anthropomorphism is employed to externalize human actions onto animals, but where zoomorphism is employed to project animals onto humans in order to externalize their cannibalism. In the zoomorphic reading, both stories are interpreted as vehicles of projection while avoiding the logical pitfall of the alternative reading.