The goal of this thesis is to explore a new clustering algorithm, VAE-Clustering, and examine if it can be applied to find differences in the distribution of stock returns and augment the distribution of a current portfolio of stocks and see how it performs in different market conditions. The VAE-clustering method is as mentioned a newly introduced method and not widely tested, especially not on time series. The first step is therefore to see if and how well the clustering works. We first apply the algorithm to a dataset containing monthly time series of the power demand in Italy. The purpose in this part is to focus on how well the method works technically. When the model works well and generates proper results with the Italian Power Demand data, we move forward and apply the model on stock return data. In the latter application we are unable to find meaningful clusters and therefore unable to move forward towards the goal of the thesis. The results shows that the VAE-clustering method is applicable for time series. The power demand have clear differences from season to season and the model can successfully identify those differences. When it comes to the financial data we hoped that the model would be able to find different market regimes based on time periods. The model is though not able distinguish different time periods from each other. We therefore conclude that the VAE-clustering method is applicable on time series data, but that the structure and setting of the financial data in this thesis makes it to hard to find meaningful clusters. The major finding is that the VAE-clustering method can be applied to time series. We highly encourage further research to find if the method can be successfully used on financial data in different settings than tested in this thesis. / Syftet med den här avhandlingen är att utforska en ny klustringsalgoritm, VAE-Clustering, och undersöka om den kan tillämpas för att hitta skillnader i fördelningen av aktieavkastningar och förändra distributionen av en nuvarande aktieportfölj och se hur den presterar under olika marknadsvillkor. VAE-klusteringsmetoden är som nämnts en nyinförd metod och inte testad i stort, särskilt inte på tidsserier. Det första steget är därför att se om och hur klusteringen fungerar. Vi tillämpar först algoritmen på ett datasätt som innehåller månatliga tidsserier för strömbehovet i Italien. Syftet med denna del är att fokusera på hur väl metoden fungerar tekniskt. När modellen fungerar bra och ger tillfredställande resultat, går vi vidare och tillämpar modellen på aktieavkastningsdata. I den senare applikationen kan vi inte hitta meningsfulla kluster och kan därför inte gå framåt mot målet som var att simulera olika marknader och se hur en nuvarande portfölj presterar under olika marknadsregimer. Resultaten visar att VAE-klustermetoden är väl tillämpbar på tidsserier. Behovet av el har tydliga skillnader från säsong till säsong och modellen kan framgångsrikt identifiera dessa skillnader. När det gäller finansiell data hoppades vi att modellen skulle kunna hitta olika marknadsregimer baserade på tidsperioder. Modellen kan dock inte skilja olika tidsperioder från varandra. Vi drar därför slutsatsen att VAE-klustermetoden är tillämplig på tidsseriedata, men att strukturen på den finansiella data som undersöktes i denna avhandling gör det svårt att hitta meningsfulla kluster. Den viktigaste upptäckten är att VAE-klustermetoden kan tillämpas på tidsserier. Vi uppmuntrar ytterligare forskning för att hitta om metoden framgångsrikt kan användas på finansiell data i andra former än de testade i denna avhandling

Dedicating less transport resources by grouping goods to be shipped together, or pooling as we name it, has a very crucial role in saving costs in transport networks. Nonetheless, it is not so easy to estimate pooling among different groups of shipments or understand why these groups are poolable. The typical solution would be to consider all shipments of both groups as one and use some Vehicle Routing Problem (VRP) software to estimate costs of the new combined group. However, this brings with it some drawbacks, such as high computational costs and no pooling explainability. On this work we build a tool that estimates the different types of pooling using demand data. This solution includes mapping shipment data to a lower dimension, where each poolability trait corresponds to a latent dimension. We tested different dimensionality reduction techniques and found that the best performing are the autoencoder models based on neural networks. Nevertheless, comparing shipments on the latent space turns out to be more challenging than expected, because distances in these latent dimensions are sometimes uncorrelated to the distances in the real shipment features. Although this limits the use cases of this approach, we still manage to build the full poolability tool that incorporates the autoencoders and uses metrics we designed to measure each poolability trait. This tool is then compared to a VRP software and proves to have close accuracy, while being much faster and explainable. / Att optimera transportresurser genom att gruppera varor som ska skickas tillsammans, även kallat poolning, spelar en avgörande roll för att spara kostnader i transportnätverk. Trots detta är det inte så enkelt att uppskatta poolning mellan olika grupper av försändelser eller förstå varför dessa grupper kan poolas. Den vanliga lösningen skulle vara att betrakta alla försändelser från båda grupperna som en enda enhet och använda mjukvara för att lösa problemet med fordonsschemaläggning (Vehicle Routing Problem, VRP) för att uppskatta kostnaderna för den nya sammanslagna gruppen. Detta medför dock vissa nackdelar, såsom höga beräkningskostnader och bristande förklarbarhet när det kommer till poolning. I detta arbete bygger vi ett verktyg som med hjälp av efterfrågedata uppskattar olika typer av poolning. Lösningen innefattar kartläggning av försändelsedata till en lägre dimension där varje egenskap för poolbarhet motsvarar en dold dimension. Vi testade olika tekniker för att minska dimensionerna och fann att de bäst presterande är autoencoder-modeller baserade på neurala nätverk. Trots detta visade det sig vara mer utmanande än förväntat att jämföra försändelser i det dolda rummet eftersom avstånden i dessa dolda dimensioner ibland inte korrelerar med avstånden i de faktiska försändelseegenskaperna. Trots att detta begränsar användningsområdena för denna metod lyckades vi ändå bygga ett komplett verktyg för poolbarhet som inkluderar autoencoders och använder metriker som vi har utformat för att mäta varje egenskap för poolbarhet. Detta verktyg jämförs sedan med en VRP-mjukvara och visar sig ha liknande noggrannhet samtidigt som det är betydligt snabbare och mer förklarligt. / Dedicare meno risorse di trasporto raggruppando insieme le merci da spedire, o creando un pool come lo chiamiamo noi, svolge un ruolo cruciale nel risparmio dei costi nelle reti di trasporto. Tuttavia, non è facile stimare il grado di aggregazione tra diversi gruppi di spedizioni o comprendere perché tali gruppi siano aggregabili. La soluzione tipica consisterebbe nel considerare tutte le spedizioni di entrambi i gruppi come una sola entità e utilizzare un software di Problema di Routing dei Veicoli (VRP) per stimare i costi del nuovo gruppo combinato. Tuttavia, ciò comporta alcuni svantaggi, come elevati costi computazionali e la mancanza di spiegazioni riguardo all'aggregazione. In questo lavoro abbiamo sviluppato uno strumento che stima i diversi tipi di aggregabilità utilizzando i dati di domanda. Questa soluzione prevede la mappatura dei dati delle spedizioni in una dimensione inferiore, in cui ciascuna caratteristica di aggregabilità corrisponde a una dimensione. Abbiamo testato diverse tecniche di riduzione dimensionale e abbiamo constatato che i modelli autoencoder basati su reti neurali sono i più efficaci. Tuttavia, confrontare le spedizioni nello spazio latente si è rivelato più complesso del previsto, poiché le distanze in queste dimensioni latenti talvolta non sono correlate alle distanze nelle caratteristiche reali delle spedizioni. Sebbene ciò limiti le applicazioni di questo approccio, siamo comunque riusciti a sviluppare uno strumento completo per l'aggregabilità che incorpora gli autoencoder e utilizza metriche da noi progettate per misurare ciascuna caratteristica di aggregabilità. Successivamente, abbiamo confrontato questo strumento con un software VRP e dimostrato che presenta un'accuratezza simile, pur essendo più veloce e fornendo spiegazioni chiare.

Today, a large amount of time series data is being produced from a variety of different devices such as smart speakers, cell phones and vehicles. This data can be used to make inferences and predictions. Neural network based methods are among one of the most popular ways to model time series data. The field of neural networks is constantly expanding and new methods and model variants are frequently introduced. In 2018, a new family of neural networks was introduced. Namely, Neural Ordinary Differential Equations (Neural ODEs). Neural ODEs have shown great potential in modelling the dynamics of temporal data. Here we present an investigation into using Neural Ordinary Differential Equations for anomaly detection. We tested two model variants, LSTM-ODE and latent-ODE. The former model utilises a neural ODE to model the continuous-time hidden state in between observations of an LSTM model, the latter is a variational autoencoder that uses the LSTM-ODE as encoding and a Neural ODE as decoding. Both models are suited for modelling sparsely and irregularly sampled time series data. Here, we test their ability to detect anomalies on various sparsity and irregularity ofthe data. The models are compared to a Gaussian mixture model, a vanilla LSTM model and an LSTM variational autoencoder. Experimental results using the Human Activity Recognition dataset showed that the Neural ODEbased models obtained a better ability to detect anomalies compared to their LSTM based counterparts. However, the computational training cost of the Neural ODE models were considerably higher than for the models that onlyutilise the LSTM architecture. The Neural ODE based methods were also more memory consuming than their LSTM counterparts. / Idag produceras en stor mängd tidsseriedata från en mängd olika enheter som smarta högtalare, mobiltelefoner och fordon. Denna datan kan användas för att dra slutsatser och förutsägelser. Neurala nätverksbaserade metoder är bland de mest populära sätten att modellera tidsseriedata. Mycket forskning inom området neurala nätverk pågår och nya metoder och modellvarianter introduceras ofta. Under 2018 introducerades en ny familj av neurala nätverk. Nämligen, Neurala Ordinära Differentialekvationer (NeuralaODE:er). Neurala ODE:er har visat en stor potential i att modellera dynamiken hos temporal data. Vi presenterar här en undersökning i att använda neuralaordinära differentialekvationer för anomalidetektion. Vi testade två olika modellvarianter, en som kallas LSTM-ODE och en annan som kallas latent-ODE.Den förstnämnda använder Neurala ODE:er för att modellera det kontinuerliga dolda tillståndet mellan observationer av en LSTM-modell, den andra är en variational autoencoder som använder LSTM-ODE som kodning och en Neural ODE som avkodning. Båda dessa modeller är lämpliga för att modellera glest och oregelbundet samplade tidsserier. Därför testas deras förmåga att upptäcka anomalier på olika gleshet och oregelbundenhet av datan. Modellerna jämförs med en gaussisk blandningsmodell, en vanlig LSTM modell och en LSTM variational autoencoder. Experimentella resultat vid användning av datasetet Human Activity Recognition (HAR) visade att de Neurala ODE-baserade modellerna erhöll en bättre förmåga att upptäcka avvikelser jämfört med deras LSTM-baserade motsvarighet. Träningstiden förde Neurala ODE-baserade modellerna var dock betydligt långsammare än träningstiden för deras LSTM-baserade motsvarighet. Neurala ODE-baserade metoder krävde också mer minnesanvändning än deras LSTM motsvarighet.

In large scale productions of metal sheets, it is important to maintain an effective way to continuously inspect the products passing through the production line. The inspection mainly consists of detection of defects and tracking of ID numbers. This thesis investigates the possibilities to create an automatic inspection system by evaluating different machine learning algorithms for defect detection and optical character recognition (OCR) on metal sheet data. Digit recognition and defect detection are solved separately, where the former compares the object detection algorithm Faster R-CNN and the classical machine learning algorithm NCGF, and the latter is based on unsupervised learning using a convolutional autoencoder (CAE). The advantage of the feature extraction method is that it only needs a couple of samples to be able to classify new digits, which is desirable in this case due to the lack of training data. Faster R-CNN, on the other hand, needs much more training data to solve the same problem. NCGF does however fail to classify noisy images and images of metal sheets containing an alloy, while Faster R-CNN seems to be a more promising solution with a final mean average precision of 98.59%. The CAE approach for defect detection showed promising result. The algorithm learned how to only reconstruct images without defects, resulting in reconstruction errors whenever a defect appears. The errors are initially classified using a basic thresholding approach, resulting in a 98.9% accuracy. However, this classifier requires supervised learning, which is why the clustering algorithm Gaussian mixture model (GMM) is investigated as well. The result shows that it should be possible to use GMM, but that it requires a lot of GPU resources to use it in an end-to-end solution with a CAE.

abstract: Image-based process monitoring has recently attracted increasing attention due to the advancement of the sensing technologies. However, existing process monitoring methods fail to fully utilize the spatial information of images due to their complex characteristics including the high dimensionality and complex spatial structures. Recent advancement of the unsupervised deep models such as a generative adversarial network (GAN) and generative adversarial autoencoder (AAE) has enabled to learn the complex spatial structures automatically. Inspired by this advancement, we propose an anomaly detection framework based on the AAE for unsupervised anomaly detection for images. AAE combines the power of GAN with the variational autoencoder, which serves as a nonlinear dimension reduction technique with regularization from the discriminator. Based on this, we propose a monitoring statistic efficiently capturing the change of the image data. The performance of the proposed AAE-based anomaly detection algorithm is validated through a simulation study and real case study for rolling defect detection. / Dissertation/Thesis / Masters Thesis Industrial Engineering 2019

Deep generative models are essential to Natural Language Processing (NLP) due to their outstanding ability to use unlabelled data, to incorporate abundant linguistic features, and to learn interpretable dependencies among data. As the structure becomes deeper and more complex, having an effective and efficient inference method becomes increasingly important. In this thesis, neural variational inference is applied to carry out inference for deep generative models. While traditional variational methods derive an analytic approximation for the intractable distributions over latent variables, here we construct an inference network conditioned on the discrete text input to provide the variational distribution. The powerful neural networks are able to approximate complicated non-linear distributions and grant the possibilities for more interesting and complicated generative models. Therefore, we develop the potential of neural variational inference and apply it to a variety of models for NLP with continuous or discrete latent variables. This thesis is divided into three parts. Part I introduces a <b>generic variational inference framework</b> for generative and conditional models of text. For continuous or discrete latent variables, we apply a continuous reparameterisation trick or the REINFORCE algorithm to build low-variance gradient estimators. To further explore Bayesian non-parametrics in deep neural networks, we propose a family of neural networks that parameterise categorical distributions with continuous latent variables. Using the stick-breaking construction, an unbounded categorical distribution is incorporated into our deep generative models which can be optimised by stochastic gradient back-propagation with a continuous reparameterisation. Part II explores <b>continuous latent variable models for NLP</b>. Chapter 3 discusses the Neural Variational Document Model (NVDM): an unsupervised generative model of text which aims to extract a continuous semantic latent variable for each document. In Chapter 4, the neural topic models modify the neural document models by parameterising categorical distributions with continuous latent variables, where the topics are explicitly modelled by discrete latent variables. The models are further extended to neural unbounded topic models with the help of stick-breaking construction, and a truncation-free variational inference method is proposed based on a Recurrent Stick-breaking construction (RSB). Chapter 5 describes the Neural Answer Selection Model (NASM) for learning a latent stochastic attention mechanism to model the semantics of question-answer pairs and predict their relatedness. Part III discusses <b>discrete latent variable models</b>. Chapter 6 introduces latent sentence compression models. The Auto-encoding Sentence Compression Model (ASC), as a discrete variational auto-encoder, generates a sentence by a sequence of discrete latent variables representing explicit words. The Forced Attention Sentence Compression Model (FSC) incorporates a combined pointer network biased towards the usage of words from source sentence, which significantly improves the performance when jointly trained with the ASC model in a semi-supervised learning fashion. Chapter 7 describes the Latent Intention Dialogue Models (LIDM) that employ a discrete latent variable to learn underlying dialogue intentions. Additionally, the latent intentions can be interpreted as actions guiding the generation of machine responses, which could be further refined autonomously by reinforcement learning. Finally, Chapter 8 summarizes our findings and directions for future work.

abstract: Feature learning and the discovery of nonlinear variation patterns in high-dimensional data is an important task in many problem domains, such as imaging, streaming data from sensors, and manufacturing. This dissertation presents several methods for learning and visualizing nonlinear variation in high-dimensional data. First, an automated method for discovering nonlinear variation patterns using deep learning autoencoders is proposed. The approach provides a functional mapping from a low-dimensional representation to the original spatially-dense data that is both interpretable and efficient with respect to preserving information. Experimental results indicate that deep learning autoencoders outperform manifold learning and principal component analysis in reproducing the original data from the learned variation sources. A key issue in using autoencoders for nonlinear variation pattern discovery is to encourage the learning of solutions where each feature represents a unique variation source, which we define as distinct features. This problem of learning distinct features is also referred to as disentangling factors of variation in the representation learning literature. The remainder of this dissertation highlights and provides solutions for this important problem. An alternating autoencoder training method is presented and a new measure motivated by orthogonal loadings in linear models is proposed to quantify feature distinctness in the nonlinear models. Simulated point cloud data and handwritten digit images illustrate that standard training methods for autoencoders consistently mix the true variation sources in the learned low-dimensional representation, whereas the alternating method produces solutions with more distinct patterns. Finally, a new regularization method for learning distinct nonlinear features using autoencoders is proposed. Motivated in-part by the properties of linear solutions, a series of learning constraints are implemented via regularization penalties during stochastic gradient descent training. These include the orthogonality of tangent vectors to the manifold, the correlation between learned features, and the distributions of the learned features. This regularized learning approach yields low-dimensional representations which can be better interpreted and used to identify the true sources of variation impacting a high-dimensional feature space. Experimental results demonstrate the effectiveness of this method for nonlinear variation pattern discovery on both simulated and real data sets. / Dissertation/Thesis / Doctoral Dissertation Industrial Engineering 2016

Indiana University-Purdue University Indianapolis (IUPUI) / Many complex processes can be viewed as sequential events on a network. In this thesis, we study the interplay between a network and the event sequences on it. We first focus on predicting events on a known network. Examples of such include: modeling retweet cascades, forecasting earthquakes, and tracing the source of a pandemic. In specific, given the network structure, we solve two types of problems - (1) forecasting future events based on the historical events, and (2) identifying the initial event(s) based on some later observations of the dynamics. The inverse problem of inferring the unknown network topology or links, based on the events, is also of great important. Examples along this line include: constructing influence networks among Twitter users from their tweets, soliciting new members to join an event based on their participation history, and recommending positions for job seekers according to their work experience. Following this direction, we study two types of problems - (1) recovering influence networks, and (2) predicting links between a node and a group of nodes, from event sequences.

Táto práca sa zameriava na analýzu vybraných častí GPON rámca pomocou algoritmov strojového učenia implementovaných pomocou knižnice TensorFlow. Vzhľadom na to, že GPON protokol je definovaný ako sada odporúčaní, implementácia naprieč spoločnosťami sa môže líšiť od navrhnutého protokolu. Preto analýza pomocou zásobníkového automatu nie je dostatočná. Hlavnou myšlienkou je vytvoriť systém modelov za použitia knižnice TensorFlow v Python3, ktoré sú schopné detekovať abnormality v komunikácií. Tieto modely používajú viaceré architektúry neuronových sietí (napr. LSTM, autoencoder) a zameriavajú sa na rôzne typy analýzy. Tento systém sa naučí na vzorovej vzorke dát a upozorní na nájdené odlišnosti v novozachytenej komunikácií. Výstupom systému odhad podobnosti aktuálnej komunikácie v porovnaní so vzorovou komunikáciou.

Magnetic resonance imaging (MRI) is a widely used medical imaging technique for examinations of the body. However, artifacts are a common problem, that must be handled for reliable diagnoses and to avoid drawing inaccurate conclusions about the contextual insights. Magnetic resonance (MR) images acquired with a Dixon-sequence enables two channels with separate fat and water content. Fat-water inversions, also called swaps, are one common artifact with this method where voxels from the two channels are swapped, producing incorrect data. This thesis investigates the possibility to use deep learning methods for an automatic detection of swaps in MR volumes. The data used in this thesis are MR volumes from UK Biobank, processed by AMRA Medical. Segmentation masks of complicated swaps are created by operators who manually annotate the swap, but only if the regions affect subsequent measurements. The segmentation masks are therefore not fully reliable, and additional synthesized swaps were created. Two different deep learning approaches were investigated, a reconstruction-based method and a segmentation-based method. The reconstruction-based networks were trained to reconstruct a volume as similar as possible to the input volume without any swaps. When testing the network on a volume with a swap, the location of the swap can be estimated from the reconstructed volume with postprocessing methods. Autoencoders is an example of a reconstruction-based network. The segmentation-based models were trained to segment a swap directly from the input volume, thus using volumes with swaps both during training and testing. The segmentation-based networks were inspired by a U-Net. The performance of the models from both approaches was evaluated on data with real and synthetic swaps with the metrics: Dice coefficient, precision, and recall. The result shows that the reconstruction-based models are not suitable for swap detection. Difficulties in finding the right architecture for the models resulted in bad reconstructions, giving unreliable predictions. Further investigations in different post-processing methods, architectures, and hyperparameters might improve swap detection. The segmentation-based models are robust with reliable detections independent of the size of the swaps, despite being trained on data with synthesized swaps. The results from the models look very promising, and can probably be used as an automated method for swap detection with some further fine-tuning of the parameters.