|
Genetic Programming in Prediction Tasks
Machač, Michal ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
This thesis introduces various machine learning algorithms which can be used in prediction tasks based on regression. Tree genetic programming and linear genetic programming are explained more thoroughly. Selected machine learning algorithms (linear regression, random forest, multilayer perceptron and tree genetic programming) are compared on publicly available datasets with the use of scikit-learn and gplearn libraries. A core part of this project is a new implementation of linear genetic programming which was developed in C++, tested on common symbolic regression problems and then evaluated on real datasets. Results obtained with the proposed system are compared with the results obtained with gplearn.
|
|
Remotely Managed Low-Energy Information Display
Petruška, Zdenko ; Mrázek, Vojtěch (referee) ; Goldmann, Tomáš (advisor)
The main goal of this thesis is to create visualization panel and an app used for management of content on this panel. Visualization panel is composed of a platform ESP32 and an E-ink display. The panel and the app communicate with each other using wireless connection. The app is written using Django web framework. The app provides management of multiple panels and displayed content can be shared by panels.
|
| |
| |
|
Arithmetic Circuit Generator
Bolješik, Michal ; Mrázek, Vojtěch (referee) ; Vašíček, Zdeněk (advisor)
The goal of this thesis is to design and implement a tool that would be able to generate a description of various types of arithmetic circuits, such as adders and multipliers, that are involved in more complex systems (filters, transformations, etc.). The first part of the thesis deals with analysis of different types of adders and multipliers on either theoretical or practical level. In the second part there is a description of the design and implementation of the tool created in Python language. On base of parameters, the tool is able to generate hierarchical or flattened description of various circuits in formats aimed for visualization, simulation and validation. In the end, the tool is used to compare different designs of adders and multipliers.
|
|
A Library for Convolutional Neural Network Design
Rek, Petr ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
In this diploma thesis, the reader is introduced to artificial neural networks and convolutional neural networks. Based on that, the design and implementation of a new library for convolutional neural networks is described. The library is then evaluated on widely used datasets and compared to other publicly available libraries. The added benefit of the library, that makes it unique, is its independence on data types. Each layer may contain up to three independent data types - for weights, for inference and for training. For the purpose of evaluating this feature, a data type with fixed point representation is also part of the library. The effects of this representation on trained net accuracy are put to a test.
|
| |
|
Evolutionary Design of Convolutional Neural Networks
Pristaš, Ján ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
The aim of this Master's thesis is to describe basic technics of evolutionary computing, convolutional neural networks (CNN), and automated design of neural networks using neuroevolution ( NAS - Neural Architecture Search ). NAS techniques are currently being researched more and more, as they speed up and simplify the lengthy and complicated process of designing artificial neural networks. These techniques are also able to search for unconventional architectures that would not be found by classic methods. The work also contains the design and implementation of software capable of automated development of convolutional neural networks using the open-source library TensorFlow. The program uses a multiobjective NSGA-II algorithm for designing accurate and compact CNNs.
|
|
The design study of nature-friendly erosion control measures in the basin
Mrázek, Vojtěch ; Sobotková, Veronika (referee) ; Dumbrovský, Miroslav (advisor)
The work is focused to design of complex erosionand flood control measures close to nature in the Bravantice Regional Office. Erosion and runoff conditions were analyzed in the given area. The DesQ-MaxQ program was used to calculate the runoff ratios in the critical point profiles. The analysis of erosion conditions was performed using GIS tools together with the USLE2D program. ArcGis was used to create graphical outputs. Based on the performed analyzes, protective measures improving erosion and runoff conditions were proposed. The evaluation of their efficiency was performed by comparing the values of the basic characteristics of direct runoff and soil erosion before and after the design of measures.
|
|
Evolutionary Optimization of Convolutional Neural Networks
Roreček, Pavel ; Mrázek, Vojtěch (referee) ; Sekanina, Lukáš (advisor)
This Master's Thesis is focused on the principles of neural networks, primarily convolutional neural networks (CNN). It introduces the evolutionary optimization in the context of neural networks. One of existing libraries devoted to the CNN design was chosen (Keras), analysed and used in image classification tasks. An optimization technique based on cartesian genetic programming that should reduce the complexity of CNN's computation was proposed and implemented. The impact of the proposed technique on CNN behaviour was evaluated in a case study.
|