This diploma's thesis is based around creating a classifier, which will be able to recognize an email communication received by Topefekt.s.r.o on daily basis and assigning it into classification class. This project will implement some of the most commonly used classification methods including machine learning. Thesis will also include evaluation comparing all used methods.

The goal of this master thesis is creation of an online system serving as a performing application for presentation results of visual geo-localization in nature and mountain environment. The system offers the users to choose one of the pre-defined photographs or~to~upload one's own photography while choosing a file or inserting an URL address. The~system will localizate a camera of a given image based on a visual geo-localization. The~geo-localization uses the mountain horizon as a key characteristic when searching for similar horizons. The~curve line of the horizon is extracted by a fully automatic algorithm based on supervised learning and dynamic programming. Visual geo-localization running on the server which using new inversed index with cache politic. This allows further scaling of the system. The server processing detected horizon curve and respond with set of the best candidates on results. Results are visualised to the user in form of classic map, detailed sattelite view and rendering of found panorama.

Hlavným zámerom tejto diplomovej práce bola automatická segmentácia lézií sklerózy multiplex na snímkoch MRI. V rámci práce boli otestované najnovšie metódy segmentácie s využitím hlbokých neurónových sietí a porovnané prístupy inicializácie váh sietí pomocou preneseného učenia (transfer learning) a samoriadeného učenia (self-supervised learning). Samotný problém automatickej segmentácie lézií sklerózy multiplex je veľmi náročný, a to primárne kvôli vysokej nevyváženosti datasetu (skeny mozgov zvyčajne obsahujú len malé množstvo poškodeného tkaniva). Ďalšou výzvou je manuálna anotácia týchto lézií, nakoľko dvaja rozdielni doktori môžu označiť iné časti mozgu ako poškodené a hodnota Dice Coefficient týchto anotácií je približne 0,86. Možnosť zjednodušenia procesu anotovania lézií automatizáciou by mohlo zlepšiť výpočet množstva lézií, čo by mohlo viesť k zlepšeniu diagnostiky individuálnych pacientov. Našim cieľom bolo navrhnutie dvoch techník využívajúcich transfer learning na predtrénovanie váh, ktoré by neskôr mohli zlepšiť výsledky terajších segmentačných modelov. Teoretická časť opisuje rozdelenie umelej inteligencie, strojového učenia a hlbokých neurónových sietí a ich využitie pri segmentácii obrazu. Následne je popísaná skleróza multiplex, jej typy, symptómy, diagnostika a liečba. Praktická časť začína predspracovaním dát. Najprv boli skeny mozgu upravené na rovnaké rozlíšenie s rovnakou veľkosťou voxelu. Dôvodom tejto úpravy bolo využitie troch odlišných datasetov, v ktorých boli skeny vytvárané rozličnými prístrojmi od rôznych výrobcov. Jeden dataset taktiež obsahoval lebku, a tak bolo nutné jej odstránenie pomocou nástroju FSL pre ponechanie samotného mozgu pacienta. Využívali sme 3D skeny (FLAIR, T1 a T2 modality), ktoré boli postupne rozdelené na individuálne 2D rezy a použité na vstup neurónovej siete s enkodér-dekodér architektúrou. Dataset na trénovanie obsahoval 6720 rezov s rozlíšením 192 x 192 pixelov (po odstránení rezov, ktorých maska neobsahovala žiadnu hodnotu). Využitá loss funkcia bola Combo loss (kombinácia Dice Loss s upravenou Cross-Entropy). Prvá metóda sa zameriavala na využitie predtrénovaných váh z ImageNet datasetu na enkodér U-Net architektúry so zamknutými váhami enkodéra, resp. bez zamknutia a následného porovnania s náhodnou inicializáciou váh. V tomto prípade sme použili len FLAIR modalitu. Transfer learning dokázalo zvýšiť sledovanú metriku z hodnoty približne 0,4 na 0,6. Rozdiel medzi zamknutými a nezamknutými váhami enkodéru sa pohyboval okolo 0,02. Druhá navrhnutá technika používala self-supervised kontext enkodér s Generative Adversarial Networks (GAN) na predtrénovanie váh. Táto sieť využívala všetky tri spomenuté modality aj s prázdnymi rezmi masiek (spolu 23040 obrázkov). Úlohou GAN siete bolo dotvoriť sken mozgu, ktorý bol prekrytý čiernou maskou v tvare šachovnice. Takto naučené váhy boli následne načítané do enkodéru na aplikáciu na náš segmentačný problém. Tento experiment nevykazoval lepšie výsledky, s hodnotou DSC 0,29 a 0,09 (nezamknuté a zamknuté váhy enkodéru). Prudké zníženie metriky mohlo byť spôsobené použitím predtrénovaných váh na vzdialených problémoch (segmentácia a self-supervised kontext enkodér), ako aj zložitosť úlohy kvôli nevyváženému datasetu.

The diploma thesis is focused on the use of artificial intelligence methods for evaluating the fault condition of machinery. The evaluated data are from a vibrodiagnostic model for simulation of static and dynamic unbalances. The machine learning methods are applied, specifically supervised learning. The thesis describes the Spyder software environment, its alternatives, and the Python programming language, in which the scripts are written. It contains an overview with a description of the libraries (Scikit-learn, SciPy, Pandas ...) and methods — K-Nearest Neighbors (KNN), Support Vector Machines (SVM), Decision Trees (DT) and Random Forests Classifiers (RF). The results of the classification are visualized in the confusion matrix for each method. The appendix includes written scripts for feature engineering, hyperparameter tuning, evaluation of learning success and classification with visualization of the result.

Le but de cette thèse est de proposer une modélisation mathématique des stimulations visuelles afin d'analyser finement des données expérimentales en psychophysique et en électrophysiologie. Plus précis\'ement, afin de pouvoir exploiter des techniques d'analyse de données issues des statistiques Bayésiennes et de l'apprentissage automatique, il est nécessaire de développer un ensemble de stimulations qui doivent être dynamiques, stochastiques et d'une complexité paramétrée. Il s'agit d'un problème important afin de comprendre la capacité du système visuel à intégrer et discriminer différents stimuli. En particulier, les mesures effectuées à de multiples échelles (neurone, population de neurones, cognition) nous permette d'étudier les sensibilités particulières des neurones, leur organisation fonctionnelle et leur impact sur la prise de décision. Dans ce but, nous proposons un ensemble de contributions théoriques, numériques et expérimentales, organisées autour de trois axes principaux : (1) un modèle de synthèse de textures dynamiques Gaussiennes spécialement paramétrée pour l'étude de la vision; (2) un modèle d'observateur Bayésien rendant compte du biais positif induit par fréquence spatiale sur la perception de la vitesse; (3) l'utilisation de méthodes d'apprentissage automatique pour l'analyse de données obtenues en imagerie optique par colorant potentiométrique et au cours d'enregistrements extra-cellulaires. Ce travail, au carrefour des neurosciences, de la psychophysique et des mathématiques, est le fruit de plusieurs collaborations interdisciplinaires. / The goal of this thesis is to propose a mathematical model of visual stimulations in order to finely analyze experimental data in psychophysics and electrophysiology. More precisely, it is necessary to develop a set of dynamic, stochastic and parametric stimulations in order to exploit data analysis techniques from Bayesian statistics and machine learning. This problem is important to understand the visual system capacity to integrate and discriminate between stimuli. In particular, the measures performed at different scales (neurons, neural population, cognition) allow to study the particular sensitivities of neurons, their functional organization and their impact on decision making. To this purpose, we propose a set of theoretical, numerical and experimental contributions organized around three principal axes: (1) a Gaussian dynamic texture synthesis model specially crafted to probe vision; (2) a Bayesian observer model that accounts for the positive effect of spatial frequency over speed perception; (3) the use of machine learning techniques to analyze voltage sensitive dye optical imaging and extracellular data. This work, at the crossroads of neurosciences, psychophysics and mathematics is the fruit of several interdisciplinary collaborations.

Le but de cette thèse CIFRE est de construire un portefeuille de stratégies de trading algorithmique intraday. Au lieu de considérer les prix comme une fonction du temps et d'un aléa généralement modélisé par un mouvement brownien, notre approche consiste à identifier les principaux signaux auxquels sont sensibles les donneurs d'ordres dans leurs prises de décision puis alors de proposer un modèle de prix afin de construire des stratégies dynamiques d'allocation de portefeuille. Dans une seconde partie plus académique, nous présentons des travaux de pricing d'options européennes et asiatiques. / The aim of this CIFRE thesis is to build a portfolio of intraday algorithmic trading strategies. Instead of considering stock prices as a function of time and a brownian motion, our approach is to identify the main signals affecting market participants when they operate on the market so we can set up a prices model and then build dynamical strategies for portfolio allocation. In a second part, we introduce several works dealing with asian and european option pricing.

Extraire une représentation de tous les facteurs de haut niveau de l'état d'un agent à partir d'informations sensorielles de bas niveau est une tâche importante, mais difficile, dans l'apprentissage automatique. Dans ce memoire, nous explorerons plusieurs approches non supervisées pour apprendre ces représentations. Nous appliquons et analysons des méthodes d'apprentissage de représentations non supervisées existantes dans des environnements d'apprentissage par renforcement, et nous apportons notre propre suite d'évaluations et notre propre méthode novatrice d'apprentissage de représentations d'état. Dans le premier chapitre de ce travail, nous passerons en revue et motiverons l'apprentissage non supervisé de représentations pour l'apprentissage automatique en général et pour l'apprentissage par renforcement. Nous introduirons ensuite un sous-domaine relativement nouveau de l'apprentissage de représentations : l'apprentissage auto-supervisé. Nous aborderons ensuite deux approches fondamentales de l'apprentissage de représentations, les méthodes génératives et les méthodes discriminatives. Plus précisément, nous nous concentrerons sur une collection de méthodes discriminantes d'apprentissage de représentations, appelées méthodes contrastives d'apprentissage de représentations non supervisées (CURL). Nous terminerons le premier chapitre en détaillant diverses approches pour évaluer l'utilité des représentations. Dans le deuxième chapitre, nous présenterons un article de workshop dans lequel nous évaluons un ensemble de méthodes d'auto-supervision standards pour les problèmes d'apprentissage par renforcement. Nous découvrons que la performance de ces représentations dépend fortement de la dynamique et de la structure de l'environnement. À ce titre, nous déterminons qu'une étude plus systématique des environnements et des méthodes est nécessaire. Notre troisième chapitre couvre notre deuxième article, Unsupervised State Representation Learning in Atari, où nous essayons d'effectuer une étude plus approfondie des méthodes d'apprentissage de représentations en apprentissage par renforcement, comme expliqué dans le deuxième chapitre. Pour faciliter une évaluation plus approfondie des représentations en apprentissage par renforcement, nous introduisons une suite de 22 jeux Atari entièrement labellisés. De plus, nous choisissons de comparer les méthodes d'apprentissage de représentations de façon plus systématique, en nous concentrant sur une comparaison entre méthodes génératives et méthodes contrastives, plutôt que les méthodes générales du deuxième chapitre choisies de façon moins systématique. Enfin, nous introduisons une nouvelle méthode contrastive, ST-DIM, qui excelle sur ces 22 jeux Atari. / Extracting a representation of all the high-level factors of an agent’s state from level-level sensory information is an important, but challenging task in machine learning. In this thesis, we will explore several unsupervised approaches for learning these state representations. We apply and analyze existing unsupervised representation learning methods in reinforcement learning environments, as well as contribute our own evaluation benchmark and our own novel state representation learning method. In the first chapter, we will overview and motivate unsupervised representation learning for machine learning in general and for reinforcement learning. We will then introduce a relatively new subfield of representation learning: self-supervised learning. We will then cover two core representation learning approaches, generative methods and discriminative methods. Specifically, we will focus on a collection of discriminative representation learning methods called contrastive unsupervised representation learning (CURL) methods. We will close the first chapter by detailing various approaches for evaluating the usefulness of representations. In the second chapter, we will present a workshop paper, where we evaluate a handful of off-the-shelf self-supervised methods in reinforcement learning problems. We discover that the performance of these representations depends heavily on the dynamics and visual structure of the environment. As such, we determine that a more systematic study of environments and methods is required. Our third chapter covers our second article, Unsupervised State Representation Learning in Atari, where we try to execute a more thorough study of representation learning methods in RL as motivated by the second chapter. To facilitate a more thorough evaluation of representations in RL we introduce a benchmark of 22 fully labelled Atari games. In addition, we choose the representation learning methods for comparison in a more systematic way by focusing on comparing generative methods with contrastive methods, instead of the less systematically chosen off-the-shelf methods from the second chapter. Finally, we introduce a new contrastive method, ST-DIM, which excels at the 22 Atari games.

Stena Recycling is one of the leading recycling companies in Sweden and at their facility in Halmstad, 300 tonnes of refuse are handled every day where aluminium is one of the most valuable materials they sort. Today, most of the sorting process is done automatically, but there are still parts of the refuse that are not correctly sorted. Approximately 4\% of the aluminium is currently not properly sorted and goes to waste. Earlier works have investigated using machine vision to help in the sorting process at Stena Recycling. However, consistently through all these previous works, there is a problem in gathering enough annotated data to train the machine learning models. This thesis aims to investigate how machine vision could be used in the recycling process and if pre-training models using self-supervised learning can alleviate the problem of gathering annotated data and yield an improvement. The results show that machine vision models could viably be used in an information system to assist operators. This thesis also shows that pre-training models with self-supervised learning may yield a small increase in performance. Furthermore, we show that models pre-trained using self-supervised learning also appear to transfer the knowledge learned from images created in a lab environment to images taken at the recycling plant.

No description available.

Indiana University-Purdue University Indianapolis (IUPUI) / Robustness and generalizability of supervised learning algorithms depend on the quality of the labeled data set in representing the real-life problem. In many real-world domains, however, we may not have full knowledge of the underlying data-generating mechanism, which may even have an evolving nature introducing new classes continually. This constitutes a partially-observed setting, where it would be impractical to obtain a labeled data set exhaustively defined by a fixed set of classes. Traditional supervised learning algorithms, assuming an exhaustive training library, would misclassify a future sample of an unobserved class with probability one, leading to an ill-defined classification problem. Our goal is to address situations where such assumption is violated by a non-exhaustive training library, which is a very realistic yet an overlooked issue in supervised learning. In this dissertation we pursue a new direction for supervised learning by defining self-adjusting models to relax the fixed model assumption imposed on classes and their distributions. We let the model adapt itself to the prospective data by dynamically adding new classes/components as data demand, which in turn gradually make the model more representative of the entire population. In this framework, we first employ suitably chosen nonparametric priors to model class distributions for observed as well as unobserved classes and then, utilize new inference methods to classify samples from observed classes and discover/model novel classes for those from unobserved classes. This thesis presents the initiating steps of an ongoing effort to address one of the most overlooked bottlenecks in supervised learning and indicates the potential for taking new perspectives in some of the most heavily studied areas of machine learning: novelty detection, online class discovery and semi-supervised learning.