The problem under investigation in this research is the development of a general approach that will establish a students knowledge level so that the student's learning can be optimized by beginning it at the most effective point. In preparation for this study, an active test with an acceptable CT3 homogeneity index was found. Two computer programs, RightOrder and MathTest, were written in Visual Basic. The latter administers the test, producing a file or responses that serves as input for the former, which performs the calculations and matrix manipulation necessary to determine the CT3 of a set of test items and construct a difficulty strata scale. The test was administered twice to the same population, the first time in the original item order. In the second administration, one item from each successive level of difficulty, beginning with the easiest, was given until the respondent answered incorrectly. Then all the remaining items were presented in order of difficulty, beginning with the easiest. The three hypothesis of this study are (a) the difficulty strata scale generated from the computerized retest, using a z-score to be determined as critical value, is congruent with that derived from the analysis done on the data of the first application of the computerized test, (b) the time spent to establish the knowledge level is shorter than the time spent taking the full test, and (c) the test, reordered according to ordering theory principles, is an accurate method of establishing a student's knowledge level.

Il y a actuellement des efforts pour faire opérer des robots dans des environnements complexes, non bornés, évoluant en permanence, au milieu ou même en coopération avec des humains. Leurs tâches peuvent être de types variés, hiérarchiques, et peuvent subir des changements radicaux ou même être créées après le déploiement du robot. Ainsi, ces robots doivent être capable d'apprendre en continu de nouvelles compétences, dans un espace non-borné, stochastique et à haute dimensionnalité. Ce type d'environnement ne peut pas être exploré en totalité, le robot va devoir organiser son exploration et décider ce qui est le plus important à apprendre ainsi que la méthode d'apprentissage. Ceci devient encore plus difficile lorsque le robot est face à des tâches à complexités variables, demandant soit une action simple ou une séquence d'actions pour être réalisées. Nous avons développé une infrastructure algorithmique d'apprentissage stratégique intrinsèquement motivé, appelée Socially Guided Intrinsic Motivation for Sequences of Actions through Hierarchical Tasks (SGIM-SAHT), apprenant la relation entre ses actions et leurs conséquences sur l'environnement. Elle organise son apprentissage, en décidant activement sur quelle tâche se concentrer, et quelle stratégie employer entre autonomes et interactives. Afin d'apprendre des tâches hiérarchiques, une architecture algorithmique appelée procédures fut développée pour découvrir et exploiter la hiérarchie des tâches, afin de combiner des compétences en fonction des tâches. L'utilisation de séquences d'actions a permis à cette architecture d'apprentissage d'adapter la complexité de ses actions à celle de la tâche étudiée. / Efforts are made to make robots operate more and more in complex unbounded ever-changing environments, alongside or even in cooperation with humans. Their tasks can be of various kinds, can be hierarchically organized, and can also change dramatically or be created, after the robot deployment. Therefore, those robots must be able to continuously learn new skills, in an unbounded, stochastic and high-dimensional space. Such environment is impossible to be completely explored during the robot's lifetime, therefore it must be able to organize its exploration and decide what is more important to learn and how to learn it, using metrics such as intrinsic motivation guiding it towards the most interesting tasks and strategies. This becomes an even bigger challenge, when the robot is faced with tasks of various complexity, some requiring a simple action to be achieved, other needing a sequence of actions to be performed. We developed a strategic intrinsically motivated learning architecture, called Socially Guided Intrinsic Motivation for Sequences of Actions through Hierarchical Tasks (SGIM-SAHT), able to learn the mapping between its actions and their outcomes on the environment. This architecture, is capable to organize its learning process, by deciding which outcome to focus on, and which strategy to use among autonomous and interactive ones. For learning hierarchical set of tasks, the architecture was provided with a framework, called procedure framework, to discover and exploit the task hierarchy and combine skills together in a task-oriented way. The use of sequences of actions enabled such a learner to adapt the complexity of its actions to that of the task at hand.

This thesis proposes an object localization and image retrieval framework, which trains a discriminative feature set for each object class. For this purpose, a hierarchical learning architecture, together with a Neighborhood Tree is introduced for object labeling. Initially, a large variety of features are extracted from the regions of the pre-segmented images. These features are, then, fed to the training module, which selects the &quot / best set of representative features&quot / , suppressing relatively less important ones for each class. During this study, we attack various problems of the current image retrieval and classification systems, including feature space design, normalization and curse of dimensionality. Above all, we elaborate the semantic gap problem in comparison to human visual system. The proposed system emulates the eye-brain channel in two layers. The first layer combines relatively simple classifiers with low level, low dimensional features. Then, the second layer implements Adaptive Resonance Theory, which extracts higher level information from the first layer. This two-layer architecture reduces the curse of dimensionality and diminishes the normalization problem. The concept of Neighborhood Tree is introduced for identifying the whole object from the over-segmented image regions. The Neighborhood Tree consists of the nodes corresponding to the neighboring regions as its children and merges the regions through a search algorithm. Experiments are performed on a set of images from Corel database, using MPEG-7, Haar and Gabor features in order to observe the power and the weakness of the proposed system. The &quot / Best Representative Features&quot / are found in the training phase using Fuzzy ARTMAP [1], Feature-based AdaBoost [2], Descriptor-based AdaBoost, Best Representative Descriptor [3], majority voting and the proposed hierarchical learning architecture. During the experiments, it is observed that the proposed hierarchical learning architecture yields better retrieval rates than the existing algorithms available in the literature.

<p dir="ltr">Learning, planning, and representing knowledge at multiple levels of temporal abstractions provide an agent with the ability to predict consequences of different courses of actions, which is essential for improving the performance of sequential decision making. However, discovering effective temporal abstractions, which the agent can use as skills, and adopting the constructed temporal abstractions for efficient policy learning can be challenging. Despite significant advancements in single-agent settings, temporal abstractions in multi-agent systems remains underexplored. This thesis addresses this research gap by introducing novel algorithms for discovering and employing temporal abstractions in both cooperative and competitive multi-agent environments. We first develop an unsupervised spectral-analysis-based discovery algorithm, aiming at finding temporal abstractions that can enhance the joint exploration of agents in complex, unknown environments for goal-achieving tasks. Subsequently, we propose a variational method that is applicable for a broader range of collaborative multi-agent tasks. This method unifies dynamic grouping and automatic multi-agent temporal abstraction discovery, and can be seamlessly integrated into the commonly-used multi-agent reinforcement learning algorithms. Further, for competitive multi-agent zero-sum games, we develop an algorithm based on Counterfactual Regret Minimization, which enables agents to form and utilize strategic abstractions akin to routine moves in chess during strategy learning, supported by solid theoretical and empirical analyses. Collectively, these contributions not only advance the understanding of multi-agent temporal abstractions but also present practical algorithms for intricate multi-agent challenges, including control, planning, and decision-making in complex scenarios.</p>

Dans cet article, nous présentons une nouvelle approche de détection multi-classes basée sur un parcours hiérarchique de classifieurs appris simultanément. Pour plus de robustesse et de rapidité, nous proposons d’utiliser un arbre de classes d’objets. Notre modèle de détection est appris en combinant les contraintes de tri et de classification dans un seul problème d’optimisation. Notre formulation convexe permet d’utiliser un algorithme de recherche pour accélérer le temps d’exécution. Nous avons mené des évaluations de notre algorithme sur les benchmarks PASCAL VOC (2007 et 2010). Comparé à l’approche un-contre-tous, notre méthode améliore les performances pour 20 classes et gagne 10x en vitesse. / Recent years have witnessed a competition in autonomous navigation for vehicles boosted by the advances in computer vision. The on-board cameras are capable of understanding the semantic content of the environment. A core component of this system is to localize and classify objects in urban scenes. There is a need to have multi-class object detection systems. Designing such an efficient system is a challenging and active research area. The algorithms can be found for applications in autonomous driving, object searches in images or video surveillance. The scale of object classes varies depending on the tasks. The datasets for object detection started with containing one class only e.g. the popular INRIA Person dataset. Nowadays, we witness an expansion of the datasets consisting of more training data or number of object classes. This thesis proposes a solution to efficiently learn a multi-class object detector. The task of such a system is to localize all instances of target object classes in an input image. We distinguish between three major efficiency criteria. First, the detection performance measures the accuracy of detection. Second, we strive low execution times during run-time. Third, we address the scalability of our novel detection framework. The two previous criteria should scale suitably with the number of input classes and the training algorithm has to take a reasonable amount of time when learning with these larger datasets. Although single-class object detection has seen a considerable improvement over the years, it still remains a challenge to create algorithms that work well with any number of classes. Most works on this subject extent these single-class detectors to work accordingly with multiple classes but remain hardly flexible to new object descriptors. Moreover, they do not consider all these three criteria at the same time. Others use a more traditional approach by iteratively executing a single-class detector for each target class which scales linearly in training time and run-time. To tackle the challenges, we present a novel framework where for an input patch during detection the closest class is ranked highest. Background labels are rejected as negative samples. The detection goal is to find the highest scoring class. To this end, we derive a convex problem formulation that combines ranking and classification constraints. The accuracy of the system is improved by hierarchically arranging the classes into a tree of classifiers. The leaf nodes represent the individual classes and the intermediate nodes called super-classes group recursively these classes together. The super-classes benefit from the shared knowledge of their descending classes. All these classifiers are learned in a joint optimization problem along with the previouslymentioned constraints. The increased number of classifiers are prohibitive to rapid execution times. The formulation of the detection goal naturally allows to use an adapted tree traversal algorithm to progressively search for the best class but reject early in the detection process the background samples and consequently reduce the system’s run-time. Our system balances between detection performance and speed-up. We further experimented with feature reduction to decrease the overhead of applying the high-level classifiers in the tree. The framework is transparent to the used object descriptor where we implemented the histogram of orientated gradients and deformable part model both introduced in [Felzenszwalb et al., 2010a]. The capabilities of our system are demonstrated on two challenging datasets containing different object categories not necessarily semantically related. We evaluate both the detection performance with different number of classes and the scalability with respect to run-time. Our experiments show that this framework fulfills the requirements of a multi-class object detector and highlights the advantages of structuring class-level knowledge.