|
|
Machine Learning of Representations in Genetic Programming
Pomykal, Šimon ; Piňos, Michal (referee) ; Sekanina, Lukáš (advisor)
The aim of this thesis is to become acquainted with machine learning methods that are used for the automatic design of representations. Specifically, the work focuses on deep learning in the field of genetic programming (GP). Image processing is chosen as a case study, particularly noise reduction methods. By combining the acquired knowledge, a new representation is proposed, intended to replace the syntactic tree in the GP algorithm. This method is obtained using a transformer-type neural network. In conclusion, a modified version of GP that works with the new representation is created. This variant is compared with the original GP using the traditional representation in several experiments.
|
|
|
Image Inpainting using Deep Learning
Zobaník, Radek ; Kubík, Tibor (referee) ; Šilling, Petr (advisor)
In this thesis, an application was developed for testing and comparing methods for completing missing parts of an image using deep learning, and two methods were trained, pconv with convolutional architecture, and AOT-GAN with GAN architecture. The thesis describes the design of the finished application, its functionality, and important implementation details. A dataset was selected on which the chosen models were optimally trained. Experiments were made on the AOT-GAN model to investigate the impact of the number of AOT blocks in generator on the resulting completed image. All experiments were qualitatively and quantitatively compared. The results showed respectable outcomes when working with natural scenery.
|
|
|
Implementing gesture recognition on ARM as an alternative to traditional device control
Gajdošík, Richard ; Zbořil, František (referee) ; Kočí, Radek (advisor)
Cieľom tejto bakalárskej práce je vývoj a implementácia systému na rozpoznávanie gest s využitím architektúry ARM, konkrétne s použitím dosky i.MX 93 a TensorFlow Lite. Projekt sa zameriava na aplikáciu neurónových sietí pre rozpoznávanie gest rúk, čím poskytuje alternatívu k tradičným metódam ovládania zariadení. Dôležitou súčasťou práce je rozsiahla analýza existujúcich riešení rozpoznávania gest, zameraná na identifikáciu ich silných stránok a možných vylepšení. Práca detailne opisuje proces navrhovania, vývoja a optimalizácie modelu na rozpoznávanie gest v reálnom čase, špeciálne prispôsobeného pre čipy ARM s dôrazom na efektivitu a výkon. Okrem toho práca aj obsahuje vytvorenie demonštračnej aplikácie, ktorá vizuálne reprezentuje rozpoznané gestá. Užívateľské testovanie je uskutočnené na hodnotenie praktickosti a užívateľského zážitku systému rozpoznávania gest, čo poskytuje cennú spätnú väzbu pre budúce vylepšenia.
|
|
|
Neural Networks for Video Quality Enhancement
Sirovatka, Matej ; Juránek, Roman (referee) ; Hradiš, Michal (advisor)
Cieľom tejto práce je vytvoriť novú metódu super rozlíšenia na zlepšenie kvality videa. Táto metóda je založená na myšlienke použitia deformovateľných konvolučných vrstiev a optického toku na zarovnanie príznakov z viacerých po sebe následujúcích snímkov videa. Táto metóda je následne použitá v neuronovej sieti založenej na U-Net architektúre na predikciu snímkov vo vysokom rozlíšení. Vyhodnotenie je prevedené na datasete obsahujúcom snímky z reálneho života a porovnané s inými metódami. Testované sú rôzne konfigurácie navrhnutej metódy a výsledky sú analyzované. Výsledky experimentov ukazujú sľubné výsledky, pričom model prekonáva bilineárnu interpoláciu a metódy založené na jednom snímku. Testované sú rôzne architektúry modulu zarovnávania príznakov spolu s celou architektúrou U-Net, pričom sa ukazuje, že použitie Vgg19 ako enkóderu dáva najlepšie výsledky.
|
|
|
Atrial fibrillation localization for burden assessment
Martinásková, Klára ; Ředina, Richard (referee) ; Filipenská, Marina (advisor)
The diploma thesis deals with the problem of detection of atrial fibrillation from ECG recordings and localization of given fibrillation segments in signals with paroxysmal fibrillation. A research is done on atrial fibrillation, the origin of this pathology and methods of fibrillation detection from ECG recordings using deep learning. Subsequently, a convolutional neural network model with residual blocks is implemented in Python to classify short (3 s) segments of the ECG signal. Subsequently, the classification results are processed and the segments with paroxysmal fibrillation are localized in the signals with fibrillation. With the classification and localization, the burden assessment of fibrillation is further evaluated. The implemented classifier on the test set achieves an F1 score of 96,15 %. When the sections with fibrillation are localized by the algorithm, MAE of 0,95 s for detecting the beginnings and 1,29 s for detecting the ends with respect to the reference positions is achieved. The estimated patient's burden assessment is compared with the actual values and achieves MAE of 3 %
|
|
|
Signature verification using neural network-based algorithms
Čírtek, Petr ; Kiac, Martin (referee) ; Myška, Vojtěch (advisor)
Signature is one of the most used biometrics in banking and contracting therefore is important to verificate signature authenticity. Verification can be done with the help of a forensic specialist or, thanks to the rise of advanced technology, with the help of a computing technology. The purpose of this thesis is to develop methods for signature verification using neural networks for Czech type of signature and to find out if adding manual extracted features to convolutional analysis could improve these methods. Neural networks seek to replicate the functioning of human brain, consisting of input neurons, several hidden layers and output neurons. Neural networks are one of the most popular artificial intelligence technologies for image analysis and classification. The proposed methods in this thesis work on the principles of convolutional networks. The first proposed method consist of three convolutional layers which extract important features from image of signature and pass them to fully connected classifier layer. This determines whether the signature is genuine or forgery. Also for this method there were created two functions which can interpret it's decision-making. The second method, siamese neural network, unlike the first, does not work with signatures independently, but uses a reference signature image to determine authenticity. The basis of this method is to extract features with convolutional analysis from both the reference signature and the signature to be authenticated. These features are then concatenated and passed to the clasificator. A Czech dataset was created to train models that would verify the Czech type of signatures. From the experiments, it was found that the addition of manualy extracted features has the potential to improve the prediction accuracy of methods based on convolutional image analysis. 3 models were trained, which can verify the Czech type of signatures with an accuracy higher than 80 \%, namely: the model of the convolutional neural network method with discrete wavelet transformation feature, which was trained on the Czech dataset, the model of the same method trained on the CEDAR dataset with number of strokes as added feature and a siamese convolutional neural network method model trained on the Czech dataset of signatures with the tri-surface feature.
|
|
|
Creating a Python-based Automated System for Recognizing Emotions from Facial Expressions.
Zima, Samuel ; Malik, Aamir Saeed (referee) ; Hussain, Yasir (advisor)
Táto práca skúma rozpoznávanie výrazu tváre (angl. facial expression recognition - FER) pomocou hlbokého učenia so zameraním na použitie v zariadeniach s obmedzenou pamäťou a výpočtovými zdrojmi. Začína výskumom emócií a výrazov tváre z psychologického, biologického a sociologického hľadiska. Jadro výskumu tvorí návrh a implementácia automatizovaného systému pre FER s použitím súboru dát FER-2013. Tento systém využíva prispôsobenú architektúru SqueezeNet rozšírenú o jednoduchý obchvat, vrstvy náhodného odpadu neurónov a vrstvy dávkovej normalizácie. Tento systém dosahuje na súbore dát FER-2013 presnosť 66,37 %. Pre porovnávaciu analýzu sa tento model porovnal s upravenou architektúrou VGG16, ktorá dosiahla presnosť 65,09 %. Táto práca poskytuje cenné poznatky o vývoji menších, efektívnejších modelov strojového učenia pre FER, ktoré sú použiteľné pre široké spektrum zariadení vrátane nízkovýkonných procesorov a vstavaných zariadení.
|
|
|
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.
|
|
|
Retinal Images Generation with a Limited Amount of Training Data
Senichak, Yahor ; Semerád, Lukáš (referee) ; Kavetskyi, Andrii (advisor)
The purpose of this study is to explore the progress and application of computer vision and generative adversarial networks (GANs3.1) in the diagnosis and study of fundus diseases. Particular attention is paid to the latest advances in the field of medical data synthesis and the development of our own algorithm. Recent advances in the deep learning architecture U-GAT-IT [22], which includes two pairs of deep neural networks (two generators and two discriminators), have been implemented. This implementation was trained for approximately 300,000 iterations, during which positive results were obtained. The dynamics of the training process were recorded and tests were performed to demonstrate the ability to generate high-quality synthetic images of the ocular background independent of the input data
|
|
|
Deep learning-based noise reduction in X-ray images
Říhová, Barbora ; Jakubíček, Roman (referee) ; Zemek, Marek (advisor)
Technologie zobrazování pomocí rentgenových paprsků je základem zkoumání vnitřní struktury velké škály objektů a výsledky mohou být právě kvůli šumu kompromitovány. Tato práce se zabývá odstraňováním šumu v rentgenových projekcích pomocí hlubokého učení, které má schopnost adaptovat se na konkrétní problém. Práce obsahuje teoretickou rešerši zaměřenou na oblasti produkce a detekce rentgenových paprsků, šumu v rentgenových snímcích a neuronových sítí. Speciální kapitola je věnována popisu vybraného řešení, které je provedeno pomocí tvorby datasetu složeného z části z modelovaných rentgenových projekcí s následně implementovaným šumem odpovídající modelu v reálných snímcích a částečně ze sérií rentgenových projekcí získaných ze zařízení Rigaku nano3DX. K implementaci byla vybrána architektura konvoluční neuronové sítě RIDNet, vzhledem k tomu, že poskytuje v oblasti redukce šumu dobré výsledky. Byly natrénovány tři modely s použitím různých částí datasetu. Nejlepší výkon byl pozorován u modelů, u kterých byla při trénování použita reálná data. Jejich účinnost je srovnatelná s tradičními metodami jako BM3D.
|
guest ::
