Advances in scaling deep learning algorithms

Les algorithmes d'apprentissage profond forment un nouvel ensemble de méthodes puissantes pour l'apprentissage automatique. L'idée est de combiner des couches de facteurs latents en hierarchies. Cela requiert souvent un coût computationel plus elevé et augmente aussi le nombre de paramètres du modèle. Ainsi, l'utilisation de ces méthodes sur des problèmes à plus grande échelle demande de réduire leur coût et aussi d'améliorer leur régularisation et leur optimization. Cette thèse adresse cette question sur ces trois perspectives. Nous étudions tout d'abord le problème de réduire le coût de certains algorithmes profonds. Nous proposons deux méthodes pour entrainer des machines de Boltzmann restreintes et des auto-encodeurs débruitants sur des distributions sparses à haute dimension. Ceci est important pour l'application de ces algorithmes pour le traitement de langues naturelles. Ces deux méthodes (Dauphin et al., 2011; Dauphin and Bengio, 2013) utilisent l'échantillonage par importance pour échantilloner l'objectif de ces modèles. Nous observons que cela réduit significativement le temps d'entrainement. L'accéleration atteint 2 ordres de magnitude sur plusieurs bancs d'essai. Deuxièmement, nous introduisont un puissant régularisateur pour les méthodes profondes. Les résultats expérimentaux démontrent qu'un bon régularisateur est crucial pour obtenir de bonnes performances avec des gros réseaux (Hinton et al., 2012). Dans Rifai et al. (2011), nous proposons un nouveau régularisateur qui combine l'apprentissage non-supervisé et la propagation de tangente (Simard et al., 1992). Cette méthode exploite des principes géometriques et permit au moment de la publication d'atteindre des résultats à l'état de l'art. Finalement, nous considérons le problème d'optimiser des surfaces non-convexes à haute dimensionalité comme celle des réseaux de neurones. Tradionellement, l'abondance de minimum locaux était considéré comme la principale difficulté dans ces problèmes. Dans Dauphin et al. (2014a) nous argumentons à partir de résultats en statistique physique, de la théorie des matrices aléatoires, de la théorie des réseaux de neurones et à partir de résultats expérimentaux qu'une difficulté plus profonde provient de la prolifération de points-selle. Dans ce papier nous proposons aussi une nouvelle méthode pour l'optimisation non-convexe.

Bodies, stories, cities : learning to read and write (in) Montréal with Gail Scott

Cette lecture, tant critique, comparative, et théorique que pédagogique, s’ancre dans le constat, premièrement, qu’il advient aux étudiantEs en littérature de se (re)poser la question des coûts et complicités qu’apprendre à lire et à écrire présuppose aujourd’hui; deuxièmement, que nos pratiques littéraires se trament au sein de lieux empreints de différences, que l’on peut nommer, selon le contexte, métaphore, récit, ville; et, troisièmement, que les efforts et investissements requis sont tout autant couteux et interminable qu’un plaisir et une nécessité politique. Ces conclusions tendent vers l’abstrait et le théorique, mais le langage en lequel elles sont articulées, langage corporel et urbain, de la dépendance et de la violence, cherche d’autant plus une qualité matérielle et concrète. Or, l’introduction propose un survol des lectures et comparaisons de Heroine de Gail Scott qui centre ce projet; identifie les contextes institutionnels, historiques, et personnels qui risquent, ensuite, de décentrer celui-ci. Le premier chapitre permet de cerner le matérialisme littéraire qui me sert de méthode par laquelle la littérature, à la fois, sollicite et offre une réponse à ces interrogations théoriques. Inspirée de l’œuvre de Gail Scott et Réjean Ducharme, premièrement, et de Walter Benjamin, Elisabeth Grosz, et Pierre Macherey ensuite, ‘matérialisme’ fait référence à cette collection de figures de pratiques littéraires et urbaines qui proviennent, par exemple, de Georges Perec, Michel DeCerteau, Barbara Johnson, et Patricia Smart, et qui invitent ensuite une réflexions sur les relations entre corporalité et narrativité, entre la nécessité et la contingence du littéraire. De plus, une collection de figures d’un Montréal littéraire et d’une cité pédagogique, acquis des œuvres de Zygmunt Bauman, Partricia Godbout, et Lewis Mumford, constitue en effet un vocabulaire nous permettant de mieux découvrir (et donc enseigner) ce que lire et apprendre requiert. Le deuxième chapitre propose une lecture comparée de Heroine et des romans des auteures québécoises Anne Dandurand, Marie Gagnon, et Tess Fragoulis, dans le contexte, premièrement, les débats entourant l’institutionnalisation de la littérature (anglo)Québécoise et, deuxièmement, des questions pédagogiques et politiques plus larges et plus urgentes que nous pose, encore aujourd’hui, cette violence récurrente qui s’acharna, par exemple, sur la Polytechnique en 1989. Or, cette intersection de la violence meurtrière, la pratique littéraire, et la pédagogie qui en résulte se pose et s’articule, encore, par le biais d’une collection de figures de styles. En fait, à travers le roman de Scott et de l’œuvre critique qui en fait la lecture, une série de craques invite à reconnaître Heroine comme étant, ce que j’appelle, un récit de dépendance, au sein duquel se concrétise une temporalité récursive et une logique d’introjection nous permettant de mieux comprendre la violence et, par conséquent, le pouvoir d’une pratique littéraire sur laquelle, ensuite, j’appuie ma pédagogie en devenir. Jetant, finalement, un regard rétrospectif sur l’oeuvre dans son entier, la conclusion de ce projet se tourne aussi vers l’avant, c’est-à-dire, vers ce que mes lectures dites matérialistes de la littérature canadienne et québécoise contribuent à mon enseignement de la langue anglaise en Corée du Sud. C’est dans ce contexte que les propos de Jacques Rancière occasionnent un dernier questionnement quant à l’historique des débats et des structures pédagogiques en Corée, d’une part, et, de l’autre, les conclusions que cette lecture de la fiction théorique de Gail Scott nous livre.

Le nombre d’Avogadro en prend pour son rhume : l’homéopathie en question.

Même si de plus en plus de psychoéducateurs utilisent des approches appuyées sur des données probantes, ils sont également confrontés dans leur pratique quotidienne à des approches dites alternatives dont la validité, dans la majorité des cas, reste à démontrer. Parmi celles-ci, l’homéopathie prétend traiter un ensemble de problèmes psychosociaux dont le TDAH, les troubles d’apprentissage, l’anxiété, la peur, etc. L’objectif de cet article est de considérer la pertinence de cette approche non seulement pour traiter les problèmes psychosociaux mais également l’ensemble des troubles qu’elle prétend soigner. Cet article comprend cinq parties. Dans la première, nous situons l’histoire de l’homéopathie dans le cadre de la chimie et de la pharmacologie modernes. La deuxième est consacrée à ce qu’il est convenu maintenant d’appeler « l’affaire de la mémoire de l’eau » que des homéopathes ont tenté de récupérer à leur profit pour justifier l’activité de leurs produits même lorsque la dilution de ceux-ci est telle qu’ils ne contiennent plus de molécule active. Au cours de la troisième partie, nous faisons état de la recherche concernant l’efficacité des traitements homéopathiques. Dans la quatrième partie, nous montrons brièvement que l’homéopathie vétérinaire n’est pas plus efficace que l’homéopathie appliquée aux humains. Dans la cinquième partie, nous soulevons quelques aspects éthiques en soulignant entre autres éléments que la prescription des produits homéopathiques et l’utilisation des « vaccins » de même nature ne sont pas sans conséquences.

Surface properties and catalytic activity of ferrospinels of nickel, cobalt and copper, prepared by soft chemical methods

Ferrospinels of nickel, cobalt and copper and their sulphated analogues were prepared by the room temperature coprecipitation route to yield samples with high surface areas. The intrinsic acidity among the ferrites was found to decrease in the order: cobalt> nickel> copper. Sulphation caused an increase in the number of weak and medium strong acid sites, whereas the strong acid sites were left unaffected. Electron donor studies revealed that copper ferrite has both the highest proportion of strong sites and the lowest proportion of weak basic sites. All the ferrite samples proved to be good catalysts for the benzoy lation of toluene with benzoyl chloride. copper and cobalt ferrites being much more active than nickel ferrite. The catalytic activity for benzoylation was not much influenced by sulphation, but it increased remarkably with calcination temperature of the catalyst. Surface Lewis acid sites, provided by the octahedral cations on the spinel surface, are suggested to be responsible for the catalytic activity for the benzoylation reaction.

Statistical Machine Learning Techniques for the Prediction of Learning Disabilities in School-Age Children

Learning Disability (LD) is a general term that describes specific kinds of learning problems. It is a neurological condition that affects a child's brain and impairs his ability to carry out one or many specific tasks. The learning disabled children are neither slow nor mentally retarded. This disorder can make it problematic for a child to learn as quickly or in the same way as some child who isn't affected by a learning disability. An affected child can have normal or above average intelligence. They may have difficulty paying attention, with reading or letter recognition, or with mathematics. It does not mean that children who have learning disabilities are less intelligent. In fact, many children who have learning disabilities are more intelligent than an average child. Learning disabilities vary from child to child. One child with LD may not have the same kind of learning problems as another child with LD. There is no cure for learning disabilities and they are life-long. However, children with LD can be high achievers and can be taught ways to get around the learning disability. In this research work, data mining using machine learning techniques are used to analyze the symptoms of LD, establish interrelationships between them and evaluate the relative importance of these symptoms. To increase the diagnostic accuracy of learning disability prediction, a knowledge based tool based on statistical machine learning or data mining techniques, with high accuracy,according to the knowledge obtained from the clinical information, is proposed. The basic idea of the developed knowledge based tool is to increase the accuracy of the learning disability assessment and reduce the time used for the same. Different statistical machine learning techniques in data mining are used in the study. Identifying the important parameters of LD prediction using the data mining techniques, identifying the hidden relationship between the symptoms of LD and estimating the relative significance of each symptoms of LD are also the parts of the objectives of this research work. The developed tool has many advantages compared to the traditional methods of using check lists in determination of learning disabilities. For improving the performance of various classifiers, we developed some preprocessing methods for the LD prediction system. A new system based on fuzzy and rough set models are also developed for LD prediction. Here also the importance of pre-processing is studied. A Graphical User Interface (GUI) is designed for developing an integrated knowledge based tool for prediction of LD as well as its degree. The designed tool stores the details of the children in the student database and retrieves their LD report as and when required. The present study undoubtedly proves the effectiveness of the tool developed based on various machine learning techniques. It also identifies the important parameters of LD and accurately predicts the learning disability in school age children. This thesis makes several major contributions in technical, general and social areas. The results are found very beneficial to the parents, teachers and the institutions. They are able to diagnose the child’s problem at an early stage and can go for the proper treatments/counseling at the correct time so as to avoid the academic and social losses.

FEATURE SELECTION AND COMPARISON OF TWO NAÏVE BAYES CLASSIFICATION METHODS IN THE CONTEXT OF SPAM FILTERING

Treating e-mail filtering as a binary text classification problem, researchers have applied several statistical learning algorithms to email corpora with promising results. This paper examines the performance of a Naive Bayes classifier using different approaches to feature selection and tokenization on different email corpora

Changing Role of Academic Libraries in the E-learning Environment: Issues and Challenges

The development of computer and network technology is changing the education scenario and transforming the teaching and learning process from the traditional physical environment to the digital environment. It is now possible to access vast amount of information online and enable one to one communication without the confines of place or time. While E-learning and teaching is unlikely to replace face-to-face training and education it is becoming an additional delivery method, providing new learning opportunities to many users. It is also causing an impact on library services as the increased use of ICT and web based learning technologies have paved the way for providing new ICT based services and resources to the users. Online learning has a crucial role in user education, information literacy programmes and in training the library professionals. It can help students become active learners, and libraries will have to play a greater role in this process of transformation. The significance of libraries within an institution has improved due to the fact that academic libraries and information services are now responsible for e-learning within their organization.

Prediction of Learning Disabilities in School Age Children using SVM and Decision Tree

This paper highlights the prediction of Learning Disabilities (LD) in school-age children using two classification methods, Support Vector Machine (SVM) and Decision Tree (DT), with an emphasis on applications of data mining. About 10% of children enrolled in school have a learning disability. Learning disability prediction in school age children is a very complicated task because it tends to be identified in elementary school where there is no one sign to be identified. By using any of the two classification methods, SVM and DT, we can easily and accurately predict LD in any child. Also, we can determine the merits and demerits of these two classifiers and the best one can be selected for the use in the relevant field. In this study, Sequential Minimal Optimization (SMO) algorithm is used in performing SVM and J48 algorithm is used in constructing decision trees.

Performance Improvement of Fuzzy and Neuro Fuzzy Systems: Prediction of Learning Disabilities in School-age Children

Learning Disability (LD) is a classification including several disorders in which a child has difficulty in learning in a typical manner, usually caused by an unknown factor or factors. LD affects about 15% of children enrolled in schools. The prediction of learning disability is a complicated task since the identification of LD from diverse features or signs is a complicated problem. There is no cure for learning disabilities and they are life-long. The problems of children with specific learning disabilities have been a cause of concern to parents and teachers for some time. The aim of this paper is to develop a new algorithm for imputing missing values and to determine the significance of the missing value imputation method and dimensionality reduction method in the performance of fuzzy and neuro fuzzy classifiers with specific emphasis on prediction of learning disabilities in school age children. In the basic assessment method for prediction of LD, checklists are generally used and the data cases thus collected fully depends on the mood of children and may have also contain redundant as well as missing values. Therefore, in this study, we are proposing a new algorithm, viz. the correlation based new algorithm for imputing the missing values and Principal Component Analysis (PCA) for reducing the irrelevant attributes. After the study, it is found that, the preprocessing methods applied by us improves the quality of data and thereby increases the accuracy of the classifiers. The system is implemented in Math works Software Mat Lab 7.10. The results obtained from this study have illustrated that the developed missing value imputation method is very good contribution in prediction system and is capable of improving the performance of a classifier.

Learning disability prediction tool using ANN and ANFIS

Learning Disability (LD) is a neurological condition that affects a child’s brain and impairs his ability to carry out one or many specific tasks. LD affects about 15 % of children enrolled in schools. The prediction of LD is a vital and intricate job. The aim of this paper is to design an effective and powerful tool, using the two intelligent methods viz., Artificial Neural Network and Adaptive Neuro-Fuzzy Inference System, for measuring the percentage of LD that affected in school-age children. In this study, we are proposing some soft computing methods in data preprocessing for improving the accuracy of the tool as well as the classifier. The data preprocessing is performed through Principal Component Analysis for attribute reduction and closest fit algorithm is used for imputing missing values. The main idea in developing the LD prediction tool is not only to predict the LD present in children but also to measure its percentage along with its class like low or minor or major. The system is implemented in Mathworks Software MatLab 7.10. The results obtained from this study have illustrated that the designed prediction system or tool is capable of measuring the LD effectively

A Reinforcement Learning Algorithm to Economic Dispatch Considering Transmission Losses

Reinforcement Learning (RL) refers to a class of learning algorithms in which learning system learns which action to take in different situations by using a scalar evaluation received from the environment on performing an action. RL has been successfully applied to many multi stage decision making problem (MDP) where in each stage the learning systems decides which action has to be taken. Economic Dispatch (ED) problem is an important scheduling problem in power systems, which decides the amount of generation to be allocated to each generating unit so that the total cost of generation is minimized without violating system constraints. In this paper we formulate economic dispatch problem as a multi stage decision making problem. In this paper, we also develop RL based algorithm to solve the ED problem. The performance of our algorithm is compared with other recent methods. The main advantage of our method is it can learn the schedule for all possible demands simultaneously.

Adaptive Real-time Anomaly-based Intrusion Detection using Data Mining and Machine Learning Techniques

Die zunehmende Vernetzung der Informations- und Kommunikationssysteme führt zu einer weiteren Erhöhung der Komplexität und damit auch zu einer weiteren Zunahme von Sicherheitslücken. Klassische Schutzmechanismen wie Firewall-Systeme und Anti-Malware-Lösungen bieten schon lange keinen Schutz mehr vor Eindringversuchen in IT-Infrastrukturen. Als ein sehr wirkungsvolles Instrument zum Schutz gegenüber Cyber-Attacken haben sich hierbei die Intrusion Detection Systeme (IDS) etabliert. Solche Systeme sammeln und analysieren Informationen von Netzwerkkomponenten und Rechnern, um ungewöhnliches Verhalten und Sicherheitsverletzungen automatisiert festzustellen. Während signatur-basierte Ansätze nur bereits bekannte Angriffsmuster detektieren können, sind anomalie-basierte IDS auch in der Lage, neue bisher unbekannte Angriffe (Zero-Day-Attacks) frühzeitig zu erkennen. Das Kernproblem von Intrusion Detection Systeme besteht jedoch in der optimalen Verarbeitung der gewaltigen Netzdaten und der Entwicklung eines in Echtzeit arbeitenden adaptiven Erkennungsmodells. Um diese Herausforderungen lösen zu können, stellt diese Dissertation ein Framework bereit, das aus zwei Hauptteilen besteht. Der erste Teil, OptiFilter genannt, verwendet ein dynamisches "Queuing Concept", um die zahlreich anfallenden Netzdaten weiter zu verarbeiten, baut fortlaufend Netzverbindungen auf, und exportiert strukturierte Input-Daten für das IDS. Den zweiten Teil stellt ein adaptiver Klassifikator dar, der ein Klassifikator-Modell basierend auf "Enhanced Growing Hierarchical Self Organizing Map" (EGHSOM), ein Modell für Netzwerk Normalzustand (NNB) und ein "Update Model" umfasst. In dem OptiFilter werden Tcpdump und SNMP traps benutzt, um die Netzwerkpakete und Hostereignisse fortlaufend zu aggregieren. Diese aggregierten Netzwerkpackete und Hostereignisse werden weiter analysiert und in Verbindungsvektoren umgewandelt. Zur Verbesserung der Erkennungsrate des adaptiven Klassifikators wird das künstliche neuronale Netz GHSOM intensiv untersucht und wesentlich weiterentwickelt. In dieser Dissertation werden unterschiedliche Ansätze vorgeschlagen und diskutiert. So wird eine classification-confidence margin threshold definiert, um die unbekannten bösartigen Verbindungen aufzudecken, die Stabilität der Wachstumstopologie durch neuartige Ansätze für die Initialisierung der Gewichtvektoren und durch die Stärkung der Winner Neuronen erhöht, und ein selbst-adaptives Verfahren eingeführt, um das Modell ständig aktualisieren zu können. Darüber hinaus besteht die Hauptaufgabe des NNB-Modells in der weiteren Untersuchung der erkannten unbekannten Verbindungen von der EGHSOM und der Überprüfung, ob sie normal sind. Jedoch, ändern sich die Netzverkehrsdaten wegen des Concept drif Phänomens ständig, was in Echtzeit zur Erzeugung nicht stationärer Netzdaten führt. Dieses Phänomen wird von dem Update-Modell besser kontrolliert. Das EGHSOM-Modell kann die neuen Anomalien effektiv erkennen und das NNB-Model passt die Änderungen in Netzdaten optimal an. Bei den experimentellen Untersuchungen hat das Framework erfolgversprechende Ergebnisse gezeigt. Im ersten Experiment wurde das Framework in Offline-Betriebsmodus evaluiert. Der OptiFilter wurde mit offline-, synthetischen- und realistischen Daten ausgewertet. Der adaptive Klassifikator wurde mit dem 10-Fold Cross Validation Verfahren evaluiert, um dessen Genauigkeit abzuschätzen. Im zweiten Experiment wurde das Framework auf einer 1 bis 10 GB Netzwerkstrecke installiert und im Online-Betriebsmodus in Echtzeit ausgewertet. Der OptiFilter hat erfolgreich die gewaltige Menge von Netzdaten in die strukturierten Verbindungsvektoren umgewandelt und der adaptive Klassifikator hat sie präzise klassifiziert. Die Vergleichsstudie zwischen dem entwickelten Framework und anderen bekannten IDS-Ansätzen zeigt, dass der vorgeschlagene IDSFramework alle anderen Ansätze übertrifft. Dies lässt sich auf folgende Kernpunkte zurückführen: Bearbeitung der gesammelten Netzdaten, Erreichung der besten Performanz (wie die Gesamtgenauigkeit), Detektieren unbekannter Verbindungen und Entwicklung des in Echtzeit arbeitenden Erkennungsmodells von Eindringversuchen.

Task-Level Robot Learning

We are investigating how to program robots so that they learn from experience. Our goal is to develop principled methods of learning that can improve a robot's performance of a wide range of dynamic tasks. We have developed task-level learning that successfully improves a robot's performance of two complex tasks, ball-throwing and juggling. With task- level learning, a robot practices a task, monitors its own performance, and uses that experience to adjust its task-level commands. This learning method serves to complement other approaches, such as model calibration, for improving robot performance.

Learning Commonsense Categorical Knowledge in a Thread Memory System

If we are to understand how we can build machines capable of broad purpose learning and reasoning, we must first aim to build systems that can represent, acquire, and reason about the kinds of commonsense knowledge that we humans have about the world. This endeavor suggests steps such as identifying the kinds of knowledge people commonly have about the world, constructing suitable knowledge representations, and exploring the mechanisms that people use to make judgments about the everyday world. In this work, I contribute to these goals by proposing an architecture for a system that can learn commonsense knowledge about the properties and behavior of objects in the world. The architecture described here augments previous machine learning systems in four ways: (1) it relies on a seven dimensional notion of context, built from information recently given to the system, to learn and reason about objects' properties; (2) it has multiple methods that it can use to reason about objects, so that when one method fails, it can fall back on others; (3) it illustrates the usefulness of reasoning about objects by thinking about their similarity to other, better known objects, and by inferring properties of objects from the categories that they belong to; and (4) it represents an attempt to build an autonomous learner and reasoner, that sets its own goals for learning about the world and deduces new facts by reflecting on its acquired knowledge. This thesis describes this architecture, as well as a first implementation, that can learn from sentences such as ``A blue bird flew to the tree'' and ``The small bird flew to the cage'' that birds can fly. One of the main contributions of this work lies in suggesting a further set of salient ideas about how we can build broader purpose commonsense artificial learners and reasoners.

A Nonparametric Approach to Pricing and Hedging Derivative Securities via Learning Networks

We propose a nonparametric method for estimating derivative financial asset pricing formulae using learning networks. To demonstrate feasibility, we first simulate Black-Scholes option prices and show that learning networks can recover the Black-Scholes formula from a two-year training set of daily options prices, and that the resulting network formula can be used successfully to both price and delta-hedge options out-of-sample. For comparison, we estimate models using four popular methods: ordinary least squares, radial basis functions, multilayer perceptrons, and projection pursuit. To illustrate practical relevance, we also apply our approach to S&P 500 futures options data from 1987 to 1991.