Le raisonnement par analogie est reconnu comme une des principales caractéristiques de l'intelligence humaine. En tant que tel, il a pendant longtemps été étudié par les philosophes et les psychologues, mais de récents travaux s'intéressent aussi à sa modélisation d'un point de vue formel à l'aide de proportions analogiques, permettant l'implémentation de programmes informatiques. Nous nous intéressons ici à l'utilisation des proportions analogiques à des fins prédictives, dans un contexte d'apprentissage artificiel. Dans de récents travaux, les classifieurs analogiques ont montré qu'ils sont capables d'obtenir d'excellentes performances sur certains problèmes artificiels, là où d'autres techniques traditionnelles d'apprentissage se montrent beaucoup moins efficaces. Partant de cette observation empirique, cette thèse s'intéresse à deux axes principaux de recherche. Le premier sera de confronter le raisonnement par proportion analogique à des applications pratiques, afin d'étudier la viabilité de l'approche analogique sur des problèmes concrets. Le second axe de recherche sera d'étudier les classifieurs analogiques d'un point de vue théorique, car jusqu'à présent ceux-ci n'étaient connus que grâce à leurs définitions algorithmiques. Les propriétés théoriques qui découleront nous permettront de comprendre plus précisément leurs forces, ainsi que leurs faiblesses. Comme domaine d'application, nous avons choisi celui des systèmes de recommandation. On reproche souvent à ces derniers de manquer de nouveauté ou de surprise dans les recommandations qui sont adressées aux utilisateurs. Le raisonnement par analogie, capable de mettre en relation des objets en apparence différents, nous est apparu comme un outil potentiel pour répondre à ce problème. Nos expériences montreront que les systèmes analogiques ont tendance à produire des recommandations d'une qualité comparable à celle des méthodes existantes, mais que leur complexité algorithmique cubique les pénalise trop fortement pour prétendre à des applications pratiques où le temps de calcul est une des contraintes principales. Du côté théorique, une contribution majeure de cette thèse est de proposer une définition fonctionnelle des classifieurs analogiques, qui a la particularité d'unifier les approches préexistantes. Cette définition fonctionnelle nous permettra de clairement identifier les liens sous-jacents entre l'approche analogique et l'approche par k plus-proches-voisins, tant au plan algorithmique de haut niveau qu'au plan des propriétés théoriques (taux d'erreur notamment). De plus, nous avons pu identifier un critère qui rend l'application de notre principe d'inférence analogique parfaitement certaine (c'est-à-dire sans erreur), exhibant ainsi les propriétés linéaires du raisonnement par analogie. / Analogical reasoning is recognized as a core component of human intelligence. It has been extensively studied from philosophical and psychological viewpoints, but recent works also address the modeling of analogical reasoning for computational purposes, particularly focused on analogical proportions. We are interested here in the use of analogical proportions for making predictions, in a machine learning context. In recent works, analogy-based classifiers have achieved noteworthy performances, in particular by performing well on some artificial problems where other traditional methods tend to fail. Starting from this empirical observation, the goal of this thesis is twofold. The first topic of research is to assess the relevance of analogical learners on real-world, practical application problems. The second topic is to exhibit meaningful theoretical properties of analogical classifiers, which were yet only empirically studied. The field of application that was chosen for assessing the suitability of analogical classifiers in real-world setting is the topic of recommender systems. A common reproach addressed towards recommender systems is that they often lack of novelty and diversity in their recommendations. As a way of establishing links between seemingly unrelated objects, analogy was thought as a way to overcome this issue. Experiments here show that while offering sometimes similar accuracy performances to those of basic classical approaches, analogical classifiers still suffer from their algorithmic complexity. On the theoretical side, a key contribution of this thesis is to provide a functional definition of analogical classifiers, that unifies the various pre-existing approaches. So far, only algorithmic definitions were known, making it difficult to lead a thorough theoretical study. From this functional definition, we clearly identified the links between our approach and that of the nearest neighbors classifiers, in terms of process and in terms of accuracy. We were also able to identify a criterion that ensures a safe application of our analogical inference principle, which allows us to characterize analogical reasoning as some sort of linear process.

This dissertation contributes to the theoretical and empirical understandings of international transmissions of exchange rate shocks. It consists of three chapters. The first chapter extends Corsetti and Dedola (2005) and further allows for competition in retail networks. In the model, there are four types of firms interacting with each other including retailing manufacturers, non-retailing manufacturers, specialised retailers and nontradable good producers. The equilibrium depends on the interaction among these four types of firms, which leads to a dynamic and incomplete exchange rate pass through (ERPT) depending on the firms’ share of retail networks. With the standard calibration, the model can generate a high (4-5) long-run trade elasticity without conflicting with a low (0.5-1) short-run elasticity, suggesting that the dynamics of retail networks offer a potential explanation of the trade elasticity puzzle. Chapter 2 investigates the ERPT of Chinese exporters. We propose an estimator that utilises orthogonal dimensions to control for unobserved marginal costs and estimate destination specific markup adjustments to bilateral and multilateral exchange rate shocks. Our estimates suggest that the cost channel accounts for roughly 50% of conventional EPRT estimates. We offer new channels of heterogeneity in firms’ pricing behaviour and provide supporting evidence on the international pricing system. Chapter 3 aims to bridge the gap between theoretical and empirical works on ERPT. I propose a machine learning algorithm that systematically detects the determinants of ERPT. The proposed algorithm is designed to work directly with highly disaggregated firm-level customs trade databases as well as publicly available commodity trade flow datasets. Tested on the simulated data from a realistic micro-founded multi-country trade model, my algorithm is proven to have accuracies around 95% and 80% in simple and complex scenarios respectively. Applying the algorithm to China’s customs data from 2000 to 2006, I document new evidence on the nonlinear relationships among market structures, unit value volatility and ERPT.

Master of Science / Department of Computer Science / William H. Hsu / Cryptocurrencies are digital currencies that have garnered significant investor attention in the financial markets. The aim of this project is to predict the daily price, particularly the daily high and closing price, of the cryptocurrency Bitcoin. This plays a vital role in making trading decisions. There exist various factors which affect the price of Bitcoin, thereby making price prediction a complex and technically challenging task. To perform prediction, we trained temporal neural networks such as time-delay neural networks (TDNN) and recurrent neural networks (RNN) on historical time series – that is, past prices of Bitcoin over several years. Features such as the opening price, highest price, lowest price, closing price, and volume of a currency over several preceding quarters were taken into consideration so as to predict the highest and closing price of the next day. We designed and implemented TDNNs and RNNs using the NeuroSolutions artificial neural network (ANN) development environment to build predictive models and evaluated them by computing various measures such as the MSE (mean square error), NMSE (normalized mean square error), and r (Pearson’s correlation coefficient) on a continuation of the training data from each time series, held out for validation.

abstract: As a promising solution to the problem of acquiring and storing large amounts of image and video data, spatial-multiplexing camera architectures have received lot of attention in the recent past. Such architectures have the attractive feature of combining a two-step process of acquisition and compression of pixel measurements in a conventional camera, into a single step. A popular variant is the single-pixel camera that obtains measurements of the scene using a pseudo-random measurement matrix. Advances in compressive sensing (CS) theory in the past decade have supplied the tools that, in theory, allow near-perfect reconstruction of an image from these measurements even for sub-Nyquist sampling rates. However, current state-of-the-art reconstruction algorithms suffer from two drawbacks -- They are (1) computationally very expensive and (2) incapable of yielding high fidelity reconstructions for high compression ratios. In computer vision, the final goal is usually to perform an inference task using the images acquired and not signal recovery. With this motivation, this thesis considers the possibility of inference directly from compressed measurements, thereby obviating the need to use expensive reconstruction algorithms. It is often the case that non-linear features are used for inference tasks in computer vision. However, currently, it is unclear how to extract such features from compressed measurements. Instead, using the theoretical basis provided by the Johnson-Lindenstrauss lemma, discriminative features using smashed correlation filters are derived and it is shown that it is indeed possible to perform reconstruction-free inference at high compression ratios with only a marginal loss in accuracy. As a specific inference problem in computer vision, face recognition is considered, mainly beyond the visible spectrum such as in the short wave infra-red region (SWIR), where sensors are expensive. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2015

abstract: Gas turbine engine for aircraft propulsion represents one of the most physics-complex and safety-critical systems in the world. Its failure diagnostic is challenging due to the complexity of the model system, difficulty involved in practical testing and the infeasibility of creating homogeneous diagnostic performance evaluation criteria for the diverse engine makes. NASA has designed and publicized a standard benchmark problem for propulsion engine gas path diagnostic that enables comparisons among different engine diagnostic approaches. Some traditional model-based approaches and novel purely data-driven approaches such as machine learning, have been applied to this problem. This study focuses on a different machine learning approach to the diagnostic problem. Some most common machine learning techniques, such as support vector machine, multi-layer perceptron, and self-organizing map are used to help gain insight into the different engine failure modes from the perspective of big data. They are organically integrated to achieve good performance based on a good understanding of the complex dataset. The study presents a new hierarchical machine learning structure to enhance classification accuracy in NASA's engine diagnostic benchmark problem. The designed hierarchical structure produces an average diagnostic accuracy of 73.6%, which outperforms comparable studies that were most recently published. / Dissertation/Thesis / Masters Thesis Electrical Engineering 2015

abstract: Information divergence functions, such as the Kullback-Leibler divergence or the Hellinger distance, play a critical role in statistical signal processing and information theory; however estimating them can be challenge. Most often, parametric assumptions are made about the two distributions to estimate the divergence of interest. In cases where no parametric model fits the data, non-parametric density estimation is used. In statistical signal processing applications, Gaussianity is usually assumed since closed-form expressions for common divergence measures have been derived for this family of distributions. Parametric assumptions are preferred when it is known that the data follows the model, however this is rarely the case in real-word scenarios. Non-parametric density estimators are characterized by a very large number of parameters that have to be tuned with costly cross-validation. In this dissertation we focus on a specific family of non-parametric estimators, called direct estimators, that bypass density estimation completely and directly estimate the quantity of interest from the data. We introduce a new divergence measure, the $D_p$-divergence, that can be estimated directly from samples without parametric assumptions on the distribution. We show that the $D_p$-divergence bounds the binary, cross-domain, and multi-class Bayes error rates and, in certain cases, provides provably tighter bounds than the Hellinger divergence. In addition, we also propose a new methodology that allows the experimenter to construct direct estimators for existing divergence measures or to construct new divergence measures with custom properties that are tailored to the application. To examine the practical efficacy of these new methods, we evaluate them in a statistical learning framework on a series of real-world data science problems involving speech-based monitoring of neuro-motor disorders. / Dissertation/Thesis / Doctoral Dissertation Electrical Engineering 2017

abstract: Online health forums provide a convenient channel for patients, caregivers, and medical professionals to share their experience, support and encourage each other, and form health communities. The fast growing content in health forums provides a large repository for people to seek valuable information. A forum user can issue a keyword query to search health forums regarding to some specific questions, e.g., what treatments are effective for a disease symptom? A medical researcher can discover medical knowledge in a timely and large-scale fashion by automatically aggregating the latest evidences emerging in health forums. This dissertation studies how to effectively discover information in health forums. Several challenges have been identified. First, the existing work relies on the syntactic information unit, such as a sentence, a post, or a thread, to bind different pieces of information in a forum. However, most of information discovery tasks should be based on the semantic information unit, a patient. For instance, given a keyword query that involves the relationship between a treatment and side effects, it is expected that the matched keywords refer to the same patient. In this work, patient-centered mining is proposed to mine patient semantic information units. In a patient information unit, the health information, such as diseases, symptoms, treatments, effects, and etc., is connected by the corresponding patient. Second, the information published in health forums has varying degree of quality. Some information includes patient-reported personal health experience, while others can be hearsay. In this work, a context-aware experience extraction framework is proposed to mine patient-reported personal health experience, which can be used for evidence-based knowledge discovery or finding patients with similar experience. At last, the proposed patient-centered and experience-aware mining framework is used to build a patient health information database for effectively discovering adverse drug reactions (ADRs) from health forums. ADRs have become a serious health problem and even a leading cause of death in the United States. Health forums provide valuable evidences in a large scale and in a timely fashion through the active participation of patients, caregivers, and doctors. Empirical evaluation shows the effectiveness of the proposed approach. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2016

abstract: A story is defined as "an actor(s) taking action(s) that culminates in a resolution(s)''. I present novel sets of features to facilitate story detection among text via supervised classification and further reveal different forms within stories via unsupervised clustering. First, I investigate the utility of a new set of semantic features compared to standard keyword features combined with statistical features, such as density of part-of-speech (POS) tags and named entities, to develop a story classifier. The proposed semantic features are based on <Subject, Verb, Object> triplets that can be extracted using a shallow parser. Experimental results show that a model of memory-based semantic linguistic features alongside statistical features achieves better accuracy. Next, I further improve the performance of story detection with a novel algorithm which aggregates the triplets producing generalized concepts and relations. A major challenge in automated text analysis is that different words are used for related concepts. Analyzing text at the surface level would treat related concepts (i.e. actors, actions, targets, and victims) as different objects, potentially missing common narrative patterns. The algorithm clusters <Subject, Verb, Object> triplets into generalized concepts by utilizing syntactic criteria based on common contexts and semantic corpus-based statistical criteria based on "contextual synonyms''. Generalized concepts representation of text (1) overcomes surface level differences (which arise when different keywords are used for related concepts) without drift, (2) leads to a higher-level semantic network representation of related stories, and (3) when used as features, they yield a significant (36%) boost in performance for the story detection task. Finally, I implement co-clustering based on generalized concepts/relations to automatically detect story forms. Overlapping generalized concepts and relationships correspond to archetypes/targets and actions that characterize story forms. I perform co-clustering of stories using standard unigrams/bigrams and generalized concepts. I show that the residual error of factorization with concept-based features is significantly lower than the error with standard keyword-based features. I also present qualitative evaluations by a subject matter expert, which suggest that concept-based features yield more coherent, distinctive and interesting story forms compared to those produced by using standard keyword-based features. / Dissertation/Thesis / Doctoral Dissertation Computer Science 2016

abstract: Machine learning methodologies are widely used in almost all aspects of software engineering. An effective machine learning model requires large amounts of data to achieve high accuracy. The data used for classification is mostly labeled, which is difficult to obtain. The dataset requires both high costs and effort to accurately label the data into different classes. With abundance of data, it becomes necessary that all the data should be labeled for its proper utilization and this work focuses on reducing the labeling effort for large dataset. The thesis presents a comparison of different classifiers performance to test if small set of labeled data can be utilized to build accurate models for high prediction rate. The use of small dataset for classification is then extended to active machine learning methodology where, first a one class classifier will predict the outliers in the data and then the outlier samples are added to a training set for support vector machine classifier for labeling the unlabeled data. The labeling of dataset can be scaled up to avoid manual labeling and building more robust machine learning methodologies. / Dissertation/Thesis / Masters Thesis Engineering 2017

Le diagnostic de fautes est essentiel pour atteindre l'objectif de temps avant mise sur le marché (time to market) des premiers prototypes de circuits intégrés. Une autre application du diagnostic est dans l'environnement de production. Les informations du diagnostic sont très utiles pour les concepteurs de circuits afin d'améliorer la conception et ainsi augmenter le rendement de production. Dans le cas où le circuit est une partie d'un système d'importance critique pour la sûreté (e.g. automobile, aérospatial), il est important que les fabricants s'engagent à identifier la source d'une défaillance dans le cas d'un retour client pour ensuite améliorer l'environnement de production afin d'éviter la récurrence d'un tel défaut et donc améliorer la sûreté. Dans le cadre de cette thèse, nous avons développé une méthodologie de modélisation et de diagnostic de fautes pour les circuits analogiques/mixtes. Une nouvelle approche basée sur l'apprentissage automatique a été proposée afin de considérer les fautes catastrophiques et paramétriques en même temps dans le diagnostic. Ensuite, nous avons focalisé sur le diagnostic de défauts spot qui sont considérés comme le mécanisme de défauts principal de circuits intégrés. Enfin, la méthodologie du diagnostic proposée a été validée par les données de circuits défectueux fournies par NXP Semiconductors - Netherlands. Mots clés: Diagnostic de fautes, modélisation de fautes, test analogique, analyse de défauts, apprentissage automatique / Fault diagnosis of ICs has grown into a special field of interest in semiconductor industry. At the design stage, diagnosing the sources of failures in IC prototypes is very critical to reduce design iterations in order to meet the time-to-market goal. In a high-volume production environment, diagnosing the sources of failures can assist the designers in gathering information regarding the underlying failure mechanisms. In cases where the IC is part of a larger system that is safety critical (e.g. automotive, aerospace), it is important to identify the root-cause of failure and apply corrective actions that will prevent failure reoccurrence and, thereby, expand the safety features. In this thesis, we have developed a methodology for fault modelling and fault diagnosis of analog/mixed circuits. A new approach has been proposed to diagnose both catastrophic and parametric faults based on machine learning. We then focused on spot defects which are more probable to occur in reality in order to develop an efficient diagnosis approach. The proposed diagnosis methodology has been demonstrated on data of failed devices provided by NXP Semiconductors - Netherlands.