Deep learning of representations and its application to computer vision

L’objectif de cette thèse par articles est de présenter modestement quelques étapes du parcours qui mènera (on espère) à une solution générale du problème de l’intelligence artificielle. Cette thèse contient quatre articles qui présentent chacun une différente nouvelle méthode d’inférence perceptive en utilisant l’apprentissage machine et, plus particulièrement, les réseaux neuronaux profonds. Chacun de ces documents met en évidence l’utilité de sa méthode proposée dans le cadre d’une tâche de vision par ordinateur. Ces méthodes sont applicables dans un contexte plus général, et dans certains cas elles on tété appliquées ailleurs, mais ceci ne sera pas abordé dans le contexte de cette de thèse. Dans le premier article, nous présentons deux nouveaux algorithmes d’inférence variationelle pour le modèle génératif d’images appelé codage parcimonieux “spike- and-slab” (CPSS). Ces méthodes d’inférence plus rapides nous permettent d’utiliser des modèles CPSS de tailles beaucoup plus grandes qu’auparavant. Nous démontrons qu’elles sont meilleures pour extraire des détecteur de caractéristiques quand très peu d’exemples étiquetés sont disponibles pour l’entraînement. Partant d’un modèle CPSS, nous construisons ensuite une architecture profonde, la machine de Boltzmann profonde partiellement dirigée (MBP-PD). Ce modèle a été conçu de manière à simplifier d’entraînement des machines de Boltzmann profondes qui nécessitent normalement une phase de pré-entraînement glouton pour chaque couche. Ce problème est réglé dans une certaine mesure, mais le coût d’inférence dans le nouveau modèle est relativement trop élevé pour permettre de l’utiliser de manière pratique. Dans le deuxième article, nous revenons au problème d’entraînement joint de machines de Boltzmann profondes. Cette fois, au lieu de changer de famille de modèles, nous introduisons un nouveau critère d’entraînement qui donne naissance aux machines de Boltzmann profondes à multiples prédictions (MBP-MP). Les MBP-MP sont entraînables en une seule étape et ont un meilleur taux de succès en classification que les MBP classiques. Elles s’entraînent aussi avec des méthodes variationelles standard au lieu de nécessiter un classificateur discriminant pour obtenir un bon taux de succès en classification. Par contre, un des inconvénients de tels modèles est leur incapacité de générer deséchantillons, mais ceci n’est pas trop grave puisque la performance de classification des machines de Boltzmann profondes n’est plus une priorité étant donné les dernières avancées en apprentissage supervisé. Malgré cela, les MBP-MP demeurent intéressantes parce qu’elles sont capable d’accomplir certaines tâches que des modèles purement supervisés ne peuvent pas faire, telles que celle de classifier des données incomplètes ou encore celle de combler intelligemment l’information manquante dans ces données incomplètes. Le travail présenté dans cette thèse s’est déroulé au milieu d’une période de transformations importantes du domaine de l’apprentissage à réseaux neuronaux profonds qui a été déclenchée par la découverte de l’algorithme de “dropout” par Geoffrey Hinton. Dropout rend possible un entraînement purement supervisé d’architectures de propagation unidirectionnel sans être exposé au danger de sur- entraînement. Le troisième article présenté dans cette thèse introduit une nouvelle fonction d’activation spécialement con ̧cue pour aller avec l’algorithme de Dropout. Cette fonction d’activation, appelée maxout, permet l’utilisation de aggrégation multi-canal dans un contexte d’apprentissage purement supervisé. Nous démontrons comment plusieurs tâches de reconnaissance d’objets sont mieux accomplies par l’utilisation de maxout. Pour terminer, sont présentons un vrai cas d’utilisation dans l’industrie pour la transcription d’adresses de maisons à plusieurs chiffres. En combinant maxout avec une nouvelle sorte de couche de sortie pour des réseaux neuronaux de convolution, nous démontrons qu’il est possible d’atteindre un taux de succès comparable à celui des humains sur un ensemble de données coriace constitué de photos prises par les voitures de Google. Ce système a été déployé avec succès chez Google pour lire environ cent million d’adresses de maisons.

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.

Using Neural Network Classifier Support Vector Machine Regression for the prediction of Melting Point of Drug – like compounds

In our study we use a kernel based classification technique, Support Vector Machine Regression for predicting the Melting Point of Drug – like compounds in terms of Topological Descriptors, Topological Charge Indices, Connectivity Indices and 2D Auto Correlations. The Machine Learning model was designed, trained and tested using a dataset of 100 compounds and it was found that an SVMReg model with RBF Kernel could predict the Melting Point with a mean absolute error 15.5854 and Root Mean Squared Error 19.7576

A Reinforcement-Learning Approach to Power Management

We describe an adaptive, mid-level approach to the wireless device power management problem. Our approach is based on reinforcement learning, a machine learning framework for autonomous agents. We describe how our framework can be applied to the power management problem in both infrastructure and ad~hoc wireless networks. From this thesis we conclude that mid-level power management policies can outperform low-level policies and are more convenient to implement than high-level policies. We also conclude that power management policies need to adapt to the user and network, and that a mid-level power management framework based on reinforcement learning fulfills these requirements.

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.

Multidimensional Adaptations for Open Learning Management Systems

Our work is focused on alleviating the workload for designers of adaptive courses on the complexity task of authoring adaptive learning designs adjusted to specific user characteristics and the user context. We propose an adaptation platform that consists in a set of intelligent agents where each agent carries out an independent adaptation task. The agents apply machine learning techniques to support the user modelling for the adaptation process

Semi-online neural-Q_leaming for real-time robot learning

Reinforcement learning (RL) is a very suitable technique for robot learning, as it can learn in unknown environments and in real-time computation. The main difficulties in adapting classic RL algorithms to robotic systems are the generalization problem and the correct observation of the Markovian state. This paper attempts to solve the generalization problem by proposing the semi-online neural-Q_learning algorithm (SONQL). The algorithm uses the classic Q_learning technique with two modifications. First, a neural network (NN) approximates the Q_function allowing the use of continuous states and actions. Second, a database of the most representative learning samples accelerates and stabilizes the convergence. The term semi-online is referred to the fact that the algorithm uses the current but also past learning samples. However, the algorithm is able to learn in real-time while the robot is interacting with the environment. The paper shows simulated results with the "mountain-car" benchmark and, also, real results with an underwater robot in a target following behavior

Using metrics from complex networks to evaluate machine translation

Establishing metrics to assess machine translation (MT) systems automatically is now crucial owing to the widespread use of MT over the web. In this study we show that such evaluation can be done by modeling text as complex networks. Specifically, we extend our previous work by employing additional metrics of complex networks, whose results were used as input for machine learning methods and allowed MT texts of distinct qualities to be distinguished. Also shown is that the node-to-node mapping between source and target texts (English-Portuguese and Spanish-Portuguese pairs) can be improved by adding further hierarchical levels for the metrics out-degree, in-degree, hierarchical common degree, cluster coefficient, inter-ring degree, intra-ring degree and convergence ratio. The results presented here amount to a proof-of-principle that the possible capturing of a wider context with the hierarchical levels may be combined with machine learning methods to yield an approach for assessing the quality of MT systems. (C) 2010 Elsevier B.V. All rights reserved.

Particle Competition and Cooperation in Networks for Semi-Supervised Learning

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Particle Competition and Cooperation in Networks for Semi-Supervised Learning with Concept Drift

Concept drift is a problem of increasing importance in machine learning and data mining. Data sets under analysis are no longer only static databases, but also data streams in which concepts and data distributions may not be stable over time. However, most learning algorithms produced so far are based on the assumption that data comes from a fixed distribution, so they are not suitable to handle concept drifts. Moreover, some concept drifts applications requires fast response, which means an algorithm must always be (re) trained with the latest available data. But the process of labeling data is usually expensive and/or time consuming when compared to unlabeled data acquisition, thus only a small fraction of the incoming data may be effectively labeled. Semi-supervised learning methods may help in this scenario, as they use both labeled and unlabeled data in the training process. However, most of them are also based on the assumption that the data is static. Therefore, semi-supervised learning with concept drifts is still an open challenge in machine learning. Recently, a particle competition and cooperation approach was used to realize graph-based semi-supervised learning from static data. In this paper, we extend that approach to handle data streams and concept drift. The result is a passive algorithm using a single classifier, which naturally adapts to concept changes, without any explicit drift detection mechanism. Its built-in mechanisms provide a natural way of learning from new data, gradually forgetting older knowledge as older labeled data items became less influent on the classification of newer data items. Some computer simulation are presented, showing the effectiveness of the proposed method.

Characterization of texture in image of skin lesions by support vector machine

Due to the increased incidence of skin cancer, computational methods based on intelligent approaches have been developed to aid dermatologists in the diagnosis of skin lesions. This paper proposes a method to classify texture in images, since it is an important feature for the successfully identification of skin lesions. For this is defined a feature vector, with the fractal dimension of images through the box-counting method (BCM), which is used with a SVM to classify the texture of the lesions in to non-irregular or irregular. With the proposed solution, we could obtain an accuracy of 72.84%. © 2012 AISTI.

Particle competition and cooperation to prevent error propagation from mislabeled data in semi-supervised learning

Semi-supervised learning is applied to classification problems where only a small portion of the data items is labeled. In these cases, the reliability of the labels is a crucial factor, because mislabeled items may propagate wrong labels to a large portion or even the entire data set. This paper aims to address this problem by presenting a graph-based (network-based) semi-supervised learning method, specifically designed to handle data sets with mislabeled samples. The method uses teams of walking particles, with competitive and cooperative behavior, for label propagation in the network constructed from the input data set. The proposed model is nature-inspired and it incorporates some features to make it robust to a considerable amount of mislabeled data items. Computer simulations show the performance of the method in the presence of different percentage of mislabeled data, in networks of different sizes and average node degree. Importantly, these simulations reveals the existence of the critical points of the mislabeled subset size, below which the network is free of wrong label contamination, but above which the mislabeled samples start to propagate their labels to the rest of the network. Moreover, numerical comparisons have been made among the proposed method and other representative graph-based semi-supervised learning methods using both artificial and real-world data sets. Interestingly, the proposed method has increasing better performance than the others as the percentage of mislabeled samples is getting larger. © 2012 IEEE.

Deep learning architecture for gesture recognition

Pós-graduação em Engenharia Mecânica - FEG

Combined active and semi-supervised learning using particle walking temporal dynamicscombined active and semi-supervised learning using particle walking temporal dynamics

Both Semi-Supervised Leaning and Active Learning are techniques used when unlabeled data is abundant, but the process of labeling them is expensive and/or time consuming. In this paper, those two machine learning techniques are combined into a single nature-inspired method. It features particles walking on a network built from the data set, using a unique random-greedy rule to select neighbors to visit. The particles, which have both competitive and cooperative behavior, are created on the network as the result of label queries. They may be created as the algorithm executes and only nodes affected by the new particles have to be updated. Therefore, it saves execution time compared to traditional active learning frameworks, in which the learning algorithm has to be executed several times. The data items to be queried are select based on information extracted from the nodes and particles temporal dynamics. Two different rules for queries are explored in this paper, one of them is based on querying by uncertainty approaches and the other is based on data and labeled nodes distribution. Each of them may perform better than the other according to some data sets peculiarities. Experimental results on some real-world data sets are provided, and the proposed method outperforms the semi-supervised learning method, from which it is derived, in all of them.

Semi-supervised learning with concept drift using particle dynamics applied to network intrusion detection data

Concept drift, which refers to non stationary learning problems over time, has increasing importance in machine learning and data mining. Many concept drift applications require fast response, which means an algorithm must always be (re)trained with the latest available data. But the process of data labeling is usually expensive and/or time consuming when compared to acquisition of unlabeled data, thus usually only a small fraction of the incoming data may be effectively labeled. Semi-supervised learning methods may help in this scenario, as they use both labeled and unlabeled data in the training process. However, most of them are based on assumptions that the data is static. Therefore, semi-supervised learning with concept drifts is still an open challenging task in machine learning. Recently, a particle competition and cooperation approach has been developed to realize graph-based semi-supervised learning from static data. We have extend that approach to handle data streams and concept drift. The result is a passive algorithm which uses a single classifier approach, naturally adapted to concept changes without any explicit drift detection mechanism. It has built-in mechanisms that provide a natural way of learning from new data, gradually "forgetting" older knowledge as older data items are no longer useful for the classification of newer data items. The proposed algorithm is applied to the KDD Cup 1999 Data of network intrusion, showing its effectiveness.