|
|
Remote laboratory for PYNQ
Veselý, Boris ; Šimek, Václav (referee) ; Mrázek, Vojtěch (advisor)
This thesis is used to provide PYNQ devices to multiple users for teaching the IVH subject. The remote laboratory application provides access to the PYNQ devices using tunnel connections. The application can manage the files stored on the server and register the time slots during which the user will be allowed to access the PYNQ devices using tunnel connections. The application also allows an administrator role that can manage users, their reservations and individual PYNQ devices. The application is written using PHP, the Nette framework and Go. The contribution of the work is to simplify access to PYNQ devices in the context of teaching the IVH subject.
|
|
|
System of Intelligent Flower Pots for Indoor Plants Growing
Kinc, Michael ; Mrázek, Vojtěch (referee) ; Šimek, Václav (advisor)
Nowadays, when technologies from the world of the Internet of Things are gaining popularity, new possibilities are opening up for the automation of common daily tasks with the help of smart devices. Such a device is also an intelligent flower pot, thanks to which the premature death of the plant can be prevented, as it may be able to warn the grower in time of deteriorating values measured from the soil or the surroundings of the monitored plant. The goal of this work is to create a system of intelligent flower pots for indoor plants growing, which can be controlled through an information system and a web application, in which the user has an overview of his flower pots, the state of the plant and the measured values.
|
|
|
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.
|
|
|
System for Electricity Consumption Registration
Hockicko, Matej ; Zachariášová, Marcela (referee) ; Mrázek, Vojtěch (advisor)
The aim of this work is to design a system to record the consumed electricity. This system will consist of an embedded device that monitors the optical output of the meter and a mobile application, which will be able to download and display the measured data using bluetooth technology. The embedded system will consist of a microcontroller from Nordic Semiconductor. The mobile application will be programmed in the Flutter framework. Historically measured data will be stored on the cloud. The focus of the design will be on the battery life of the embedded device, which will be powered by a CR2032 battery. The main benefit of this work is the ability to monitor electricity consumption using the embedded device and mobile application without the need of owning a smart meter.
|
|
|
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.
|
|
|
Visual Programming Toolkit Based on MicroPython for ESP32 Platform
Paul, Daniel ; Mrázek, Vojtěch (referee) ; Šimek, Václav (advisor)
Táto diplomová práca predstavuje vývoj Vizuálneho Programovacieho Nástroja určeného na programovanie platformy ESP32 pomocou MicroPythonu. Nástroj využíva intuitívnu povahu paradigmy vizuálneho programovania na zjednodušenie procesu programovania mikrokontrolérov pre používateľov bez rozsiahlych skúseností s programovaním. Jadro programovacieho nástroju je postavené na webovom rozhraní, ktoré využíva knižnicu ReactFlow na umožnenie funkcie "tahaj a pusť" s diagramami založenými na toku, čo umožňuje používateľom zostavovať kód prostredníctvom vizuálnych blokov, ktoré predstavujú príkazy a štruktúry jazyka MicroPython. Ďalej pokrýva backend umiestnený na samotnom zariadení ESP32, ktorý umožňuje komunikáciu s frontendovým klientom.
|
|
|
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 system for domestic chicken farming
Kejík, Pavel ; Šimek, Václav (referee) ; Mrázek, Vojtěch (advisor)
The aim of this thesis was to design and construct devices for automating chicken farming. The devices should be competitive in terms of both price and features compared to those available on the market. The described devices provide wireless connectivity, so they are considered IoT devices. An overview of available IoT protocols is provided in the thesis. Additionally, devices available on the market and their features, which are set as the minimum requirements for the design of the implemented devices, are mentioned. The practical implementation of these devices is divided into descriptions of the mechanical and electronic construction, as well as the software. Specific approaches to control are explained in detail. The devices were developed into fully functional prototypes. Prototype tests were conducted for several weeks in simulated conditions without the presence of chickens to avoid contamination.
|
|
|
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.
|
guest ::
RSS feed.