|
|
Evolutionary Design of Neural Networks
Kastner, Jan ; Hurta, Martin (referee) ; Sekanina, Lukáš (advisor)
The thesis deals with the implementation of a problem-solving method for the automated design of convolutional neural networks (CNN) architectures. The optimization of two fundamental and often conflicting characteristics, the number of parameters and the quality of CNN classification, is performed using a multi-criteria optimization genetic algorithm (NSGA-II). To encode this problem, the Cartesian genetic programming (CGP) technique is used, which enables the wide range of CNN architectures to be represented, and at the same time, the searched area can be appropriately limited by parameterization. Experiments were performed on the MNIST dataset to understand the effect of population size on the quality of the resulting solution. It is also evident from the results of the experiments that the quality of the architectures found can compete with already established models. This is therefore an alternative approach that does not require human intervention compared to manual design.
|
|
| |
|
|
Aproximace obvodů s využitím alternativních reprezentací
Michalisko, Tomáš ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
This master's thesis deals with the design of approximate circuits using alternative representations. The investigated representations include the And-inverter graph, Majority-Inverter graph, and Xor-Majority graph. Cartesian genetic programming is employed for design automation. By computing the approximation error using formal methods, the developed system can be applied to more complex circuits. In the first part of the experiments, the speed of the program is evaluated and optimized. Subsequently, a suitable mutation operator is searched for. Then, the system is tested for approximating 8-bit multipliers and 16-bit adders with the aim of minimizing size and delay. The results show that adders and multipliers in the XMG representation achieve better fitness values compared to evolution at the gate level. Finally, an evolution targeting the k-LUT technology is performed. Here, gates remain the most efficient representation.
|
|
|
Evolutionary Design of Non-Linear Functions for Convolutional Neural Networks
Hladiš, Martin ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
The aim of this thesis is to design and implement a program for automated design of nonlinear activation functions for convolutional neural networks (CNN) using evolutionary algorithms. The use of automated design provides an independent view to systematically explore a wide range of activation functions and identify the best ones. The method for automatic design chosen in this thesis is a form of evolutionary algorithms referred to as Cartesian genetic programming, which uses a graph representation to encode the solution. This technique allows for the definition of a set of mathematical primitives that define the search space, and thus simply parameterize the design. The implemented approach has been tested on several different architectures and datasets (LeNet-5 \& MNIST, ResNet-10 \& FashionMNIST, WRN-40-4 \& CIFAR-10). Experiments have shown that the approach can find activation functions that statistically improve the accuracy of the architecture over the commonly used ReLU function.
|
|
|
Využití operátoru křížení v kartézském genetickém programování
Bromnik, Petr ; Sekanina, Lukáš (referee) ; Hurta, Martin (advisor)
The aim of this paper is to propose and implement two new crossover methods in Cartesian Genetic Programming (CGP) and compare them with existing approaches. CGP is a type of evolutionary algorithm that uses acyclic graphs to represent executable programs. Most CGP applications use the mutation operator only, but the effort to find a suitable crossover operator is still ongoing. In this paper, the two newly proposed crossover methods are compared on five symbolic regression problems against the standard 1 + lambda procedure based purely on mutation. Experimental results show that these methods find solutions in a similar number of fitness evaluations as 1 + lambda and, in two cases, even significantly earlier.
|
|
|
Genetic Programming with Memory for Symbolic Regression
Jůza, Tadeáš ; Bidlo, Michal (referee) ; Sekanina, Lukáš (advisor)
The purpose of this thesis is to evaluate the possibility of extending genetic programming with memory for solving symbolic regression problems. Furthermore, a set of problems for testing the quality of such solutions is developed. The thesis proposes a practical application of such an extension to reduce the energy consumption of loading weights of convolutional neural networks. Instead of retrieving all the weights of the network from external memory, only a small percentage of the weights is retrieved and the remaining ones are generated using the evolved expression. This method was primarily evaluated on reducing the set of weights of convolutional layers of a small convolutional neural network classifying the MNIST dataset. Furthermore, the possibility of generating weights was also tested on other convolutional neural networks solving more complex classification problems. The proposed method has delivered interesting tradeoffs between the classification accuracy and weight memory size.
|
|
|
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.
|
|
|
GUI for Handling Genetic Programming Chromozome
Staurovská, Jana ; Žaloudek, Luděk (referee) ; Jaroš, Jiří (advisor)
The main goal of this thesis is to create a program for manipulation with genetic programming chromosomes, which should allow export to a vector graphics format, moving of gates, their colouring and other graphical operations, and will work on different operating systems (mainly Microsoft Windows and Linux). For better understanding, the basic principles of cartesian genetic programming are described in theoretical part.
|
|
|
Genetic Programming for Design of Digital Circuits
Hejtmánek, Michal ; Bidlo, Michal (referee) ; Gajda, Zbyšek (advisor)
The goal of this work was the study of evolutionary algorithms and utilization of them for digital circuit design. Especially, a genetic programming and its different manipulation with building blocks is mentioned in contrast to a genetic algorithm. On the basis of this approach, I created and tested a hybrid method of electronic circuit design. This method uses spread schemes according to the genetic algorithm for the pattern problems witch are solved by the genetic programming. The method is more successful and have faster convergence to a solution in difficult electronic circuits design than a common algorithm of the genetic programming.
|
|
|
Automated Multi-Objective Parallel Evolutionary Circuit Design and Approximation
Hrbáček, Radek ; Fišer, Petr (referee) ; Trefzer,, Martin (referee) ; Sekanina, Lukáš (advisor)
Spotřeba a energetická efektivita se stává jedním z nejdůležitějších parametrů při návrhu počítačových systémů, zejména kvůli omezené kapacitě napájení u zařízení napájených bateriemi a velmi vysoké spotřebě energie rostoucích datacenter a cloudové infrastruktury. Současně jsou uživatelé ochotni do určité míry tolerovat nepřesné nebo chybné výpočty v roustoucím počtu aplikací díky nedokonalostem lidských smyslů, statistické povaze výpočtů, šumu ve vstupních datech apod. Přibližné počítání, nová oblast výzkumu v počítačovém inženýrství, využívá rozvolnění požadavků na funkčnost za účelem zvýšení efektivity počítačových systémů, pokud jde o spotřebu energie, výpočetní výkon či složitost. Aplikace tolerující chyby mohou být implementovány efektivněji a stále sloužit svému účelu se stejnou nebo mírně sníženou kvalitou. Ačkoli se objevují nové metody pro návrh přibližně počítajících výpočetních systémů, je stále nedostatek automatických návrhových metod, které by nabízely velké množství kompromisních řešení dané úlohy. Konvenční metody navíc často produkují řešení, která jsou daleko od optima. Evoluční algoritmy sice přinášejí inovativní řešení složitých optimalizačních a návrhových problémů, nicméně trpí několika nedostatky, např. nízkou škálovatelností či vysokým počtem generací nutných k dosažení konkurenceschopných výsledků. Pro přibližné počítání je vhodný zejména multikriteriální návrh, což existující metody většinou nepodporují. V této práci je představen nový automatický multikriteriální paralelní evoluční algoritmus pro návrh a aproximaci digitálních obvodů. Metoda je založena na kartézském genetickém programování, pro zvýšení škálovatelnosti byla navržena nová vysoce paralelizovaná implementace. Multikriteriální návrh byl založen na principech algoritmu NSGA-II. Výkonnost implementace byla vyhodnocena na několika různých úlohách, konkrétně při návrhu (přibližně počítajících) aritmetických obvodů, Booleovských funkcích s vysokou nelinearitou či přibližných logických obvodů pro tří-modulovou redundanci. V těchto úlohách bylo dosaženo význammých zlepšení ve srovnání se současnými metodami.
|
guest ::
