|
|
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.
|
|
|
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.
|
|
| |
|
|
Diffusion Evolutionary Algorithm
Mészáros, István ; Pospíchal, Petr (referee) ; Jaroš, Jiří (advisor)
There are new trends in artificial intelligence nowadays. Methods known as evolutionary algorithms are one of them. These algorithms allow us to design and optimize systems using computers. One of the variants of evolutionary algorithms is the diffusion evolutionary algorithm. This type of algorithms is able to run in parallel, and besides that it brings many positive features. The question is under what conditions the diffusion variant of evolutionary algorithms can effectively be used. Is it possible to use for planning systems and for problem optimization? Why are they more favorable than other types of evolutionary algorithms? This work tries to answer these questions and explain the behavior of these algorithms.
|
|
|
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.
|
|
|
Intelligent Web Work Planner
Kmeť, Miroslav ; Vrábel, Lukáš (referee) ; Čermák, Martin (advisor)
This thesis describes basic principles governing the use of evolutionary algorithms. Thesis deals with the usage of the evolutionary algorithms for scheduling the work between group of employees. Genetic algorithms, which represents intelligent stochastic optimization techniques based on the mechanism of natural selection and genetics are mainly used to solve this problem. Each solution is represented as an individual in population and only the most adapted ones are selected for the process of reproduction.
|
|
| |
guest ::
