|
|
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.
|
|
|
Implementation and Comparison of Nature-Inspired Search Algorithms
Malysák, Adam ; Husa, Jakub (referee) ; Sekanina, Lukáš (advisor)
This thesis deals with the description, implementation and comparison of genetic algorithm, genetic algorithm enhanced with local search heuristic and binary particle swarm optimization (BPSO). These are algorithms inspired by natural phenomena, specifically the evolution and movement of bird flocks or fish schools. Implemented algorithms are used to solve the 3-SAT problem, which is also described in this thesis. Algorithms are tested on 3-SAT benchmarks and compared to each other and to other papers.
|
|
|
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.
|
|
|
Optimization algorithms for inverse heat exchange problems
Ibehej, David ; Dobrovský, Ladislav (referee) ; Kůdela, Jakub (advisor)
This thesis addresses the issue of inverse heat transfer and its solution through optimization. The study focuses on the application of various evolutionary algorithms and their combinations, which are implemented and used to solve the selected problem. In the practical part, models approximating the curve of the material’s effective thermal capacity are designed, and these models are optimized using evolutionary algorithms with the aim of minimizing the difference between simulated and experimental data. Finally, the resulting models and algorithms are compared in terms of their accuracy and efficiency.
|
|
|
Automated compression of neural network weights
Lorinc, Marián ; Sekanina, Lukáš (referee) ; Mrázek, Vojtěch (advisor)
Konvolučné neurónové siete (CNN) od svojho vynájdenia zrevolucionizovali spôsob, akým sa realizujú úlohy z odvetvia počítačového videnia. Vynález CNN viedol k zníženiu pamäťovej náročnosti, keďže váhy boli nahradené konvolučnými filtrami obsahujúcimi menej trénovateľných váh. Avšak, toto zníženie bolo dosiahnuté na úkor zvýšenia požiadaviek na výpočtový výkon, ktorý je naviazaný na výpočet konvolúcie. Táto práca skúma hypotézu, či je možné sa vyhnúť načítavaniu váh a miesto toho ich vypočítať, čím sa ušetrí energia. Na otestovanie tejto hypotézy bol vyvinutý nový algoritmus kompresie váh využívajúci Kartézske genetické programovanie. Tento algoritmus hľadá najoptimálnejšiu funkciu kompresie váh s cieľom zvýšiť energetickú účinnosť. Experimenty vykonané na architektúrach LeNet-5 a MobileNetV2 ukázali, že algoritmus dokáže efektívne znížiť spotrebu energie pri zachovaní vysokej presnosti modelu. Výsledky ukázali, že určité vrstvy je možné doplniť vypočítanými váhami, čo potvrdzuje potenciál pre energeticky efektívne neurónové siete.
|
|
|
Automated Representation Learning for Cartesian Genetic Programming Using Neural Networks
Koči, Martin ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
This master's thesis addresses the integration of neural networks and Cartesian Genetic Programming (CGP). It explores the use of neural networks for automated representation creation for CGP and their application to improve the evolutionary process in CGP. The study covers basic concepts of machine learning, including various types of learning and neural network models. It also touches on evolutionary algorithms with an emphasis on their basic principles, general algorithms, and types of representations. This work also includes principles of representation learning and two fundamental architectures for their creation. It describes the subsequent use of representation learning in genetic programming. The solution design includes data acquisition and preprocessing, representation creation processes, and the utilization of the resulting representations. The thesis also implements two new approaches for creating representations for Cartesian genetic programs. It further explores their use in two new mutation operators, where one is based on direct modification of the vector representation and the other on the selection of genes for mutation based on their similarity. The last of the explored areas is predicting the suitability of candidate solutions using newly emerged representations.
|
|
|
Srovnání metod operátoru křížení v kartézském genetickém programování
Fedorová, Ela ; Mrázek, Vojtěch (referee) ; Hurta, Martin (advisor)
This thesis deals with the crossover operator in Cartesian genetic programming. The aim of the thesis is to investigate and compare the use of different crossover methods. The thesis focuses on analyzing the behavior and effectiveness of selected methods on symbolic regression problems. My own implementation of three crossover methods, namely the subgraph method, block method and discrete recombination, was used. For these methods, experiments were performed to monitor the number of generations to find a solution and the quality of the solution found. The results indicate the potential of all three investigated methods to improve CGP performance and point to the subgraph method as the most useful in the given experimental setting.
|
|
|
Evolutionary Design of Local Image FIlters
Gall, Samuel ; Hurta, Martin (referee) ; Sekanina, Lukáš (advisor)
This thesis focuses on the research and implementation of evolutionary design of local image filters. The aim is to create a tool capable of automatically designing suitable image operators for image filtering, specifically noise removal, using an evolutionary design method called Cartesian Genetic Programming (CGP). The tool was used for various experiments with different settings of CGP parameters such as grid size, population size, and mutation parameter. The created filters were compared with conventional noise removal filters. Evolved filters were tested on a set of test images, where their behavior was comparable to that of a median filter. Unlike the median filter, evolved filters were able to preserve more image quality.
|
|
|
Evolutionary Design of Convolutional Neural Networks Utilizing a Supernet
Lamačka, Zbyněk ; Piňos, Michal (referee) ; Sekanina, Lukáš (advisor)
This work explores the possibilities of automated design and optimization of convolutional neural networks (CNNs) using evolutionary algorithms with the concept of Neural Architecture Search (NAS). NAS methods facilitate the work of neural network architects and allow access to neural networks by people who would not normally have access to them. Architectures that are created by automated methods are able to outperform architectures that were created by experienced architects. These methods are not bound by conventional design approaches, and therefore innovative architectures can emerge. The goal of this work is to design and implement a neuroevolutionary method using a supernetwork. The supernetwork concept aims to make the process of automatic network design faster and cheaper. This method will be evaluated based on the architectures it generates. The evaluation of the architectures considers two criteria -- accuracy and complexity of the network. The ImageNet dataset is used for the evaluation.
|
|
| |
guest ::
