Environnement d’adaptation pour un jeu sérieux

Nous avons développé un jeu sérieux afin d’enseigner aux utilisateurs à dessiner des diagrammes de Lewis. Nous l’avons augmenté d’un environnement pouvant enregistrer des signaux électroencéphalographiques, les expressions faciales, et la pupille d’un utilisateur. Le but de ce travail est de vérifier si l’environnement peut permettre au jeu de s’adapter en temps réel à l’utilisateur grâce à une détection automatique du besoin d’aide de l’utilisateur ainsi que si l’utilisateur est davantage satisfait de son expérience avec l’adaptation. Les résultats démontrent que le système d’adaptation peut détecter le besoin d’aide grâce à deux modèles d’apprentissage machine entraînés différemment, l’un généralisé et l’autre personalisé, avec des performances respectives de 53.4% et 67.5% par rapport à un niveau de chance de 33.3%.

Environnement d’adaptation pour un jeu sérieux

Nous avons développé un jeu sérieux afin d’enseigner aux utilisateurs à dessiner des diagrammes de Lewis. Nous l’avons augmenté d’un environnement pouvant enregistrer des signaux électroencéphalographiques, les expressions faciales, et la pupille d’un utilisateur. Le but de ce travail est de vérifier si l’environnement peut permettre au jeu de s’adapter en temps réel à l’utilisateur grâce à une détection automatique du besoin d’aide de l’utilisateur ainsi que si l’utilisateur est davantage satisfait de son expérience avec l’adaptation. Les résultats démontrent que le système d’adaptation peut détecter le besoin d’aide grâce à deux modèles d’apprentissage machine entraînés différemment, l’un généralisé et l’autre personalisé, avec des performances respectives de 53.4% et 67.5% par rapport à un niveau de chance de 33.3%.

Researching the Use of Communication Technologies in Higher Education Institutions in Portugal

This paper describes a research which main purpose was identifying and characterizing the use of Communication Technologies by Portuguese Public Higher Education Institutions to support learning activities. An analysis model was created and used to develop a nationwide online survey used to collect data from students, teachers and institutional managers. The results show that institutional policies and resources are in place and being used to support learning; learning management systems and interpersonal communication technologies are intensely used and widely adopted; and that there are gender differences as far as the students' use of Communication Technologies is concerned. The results of this project provide a useful insight on the use of Communication Technologies by Portuguese Public Higher Education Institutions and give valuable information for ongoing decision making processes regarding the institutional adoption and development of learning models that take advantage of these technologies.

Towards Unstructured Knowledge Integration in Natural Language Processing

In the last decades, Artificial Intelligence has witnessed multiple breakthroughs in deep learning. In particular, purely data-driven approaches have opened to a wide variety of successful applications due to the large availability of data. Nonetheless, the integration of prior knowledge is still required to compensate for specific issues like lack of generalization from limited data, fairness, robustness, and biases. In this thesis, we analyze the methodology of integrating knowledge into deep learning models in the field of Natural Language Processing (NLP). We start by remarking on the importance of knowledge integration. We highlight the possible shortcomings of these approaches and investigate the implications of integrating unstructured textual knowledge. We introduce Unstructured Knowledge Integration (UKI) as the process of integrating unstructured knowledge into machine learning models. We discuss UKI in the field of NLP, where knowledge is represented in a natural language format. We identify UKI as a complex process comprised of multiple sub-processes, different knowledge types, and knowledge integration properties to guarantee. We remark on the challenges of integrating unstructured textual knowledge and bridge connections with well-known research areas in NLP. We provide a unified vision of structured knowledge extraction (KE) and UKI by identifying KE as a sub-process of UKI. We investigate some challenging scenarios where structured knowledge is not a feasible prior assumption and formulate each task from the point of view of UKI. We adopt simple yet effective neural architectures and discuss the challenges of such an approach. Finally, we identify KE as a form of symbolic representation. From this perspective, we remark on the need of defining sophisticated UKI processes to verify the validity of knowledge integration. To this end, we foresee frameworks capable of combining symbolic and sub-symbolic representations for learning as a solution.

Data-driven and data-oriented methods for materials science and technologies

The discovery of new materials and their functions has always been a fundamental component of technological progress. Nowadays, the quest for new materials is stronger than ever: sustainability, medicine, robotics and electronics are all key assets which depend on the ability to create specifically tailored materials. However, designing materials with desired properties is a difficult task, and the complexity of the discipline makes it difficult to identify general criteria. While scientists developed a set of best practices (often based on experience and expertise), this is still a trial-and-error process. This becomes even more complex when dealing with advanced functional materials. Their properties depend on structural and morphological features, which in turn depend on fabrication procedures and environment, and subtle alterations leads to dramatically different results. Because of this, materials modeling and design is one of the most prolific research fields. Many techniques and instruments are continuously developed to enable new possibilities, both in the experimental and computational realms. Scientists strive to enforce cutting-edge technologies in order to make progress. However, the field is strongly affected by unorganized file management, proliferation of custom data formats and storage procedures, both in experimental and computational research. Results are difficult to find, interpret and re-use, and a huge amount of time is spent interpreting and re-organizing data. This also strongly limit the application of data-driven and machine learning techniques. This work introduces possible solutions to the problems described above. Specifically, it talks about developing features for specific classes of advanced materials and use them to train machine learning models and accelerate computational predictions for molecular compounds; developing method for organizing non homogeneous materials data; automate the process of using devices simulations to train machine learning models; dealing with scattered experimental data and use them to discover new patterns.

Development and testing of methodologies for the control and diagnosis of innovative combustion systems

In pursuit of aligning with the European Union's ambitious target of achieving a carbon-neutral economy by 2050, researchers, vehicle manufacturers, and original equipment manufacturers have been at the forefront of exploring cutting-edge technologies for internal combustion engines. The introduction of these technologies has significantly increased the effort required to calibrate the models implemented in the engine control units. Consequently the development of tools that reduce costs and the time required during the experimental phases, has become imperative. Additionally, to comply with ever-stricter limits on 〖"CO" 〗_"2" emissions, it is crucial to develop advanced control systems that enhance traditional engine management systems in order to reduce fuel consumption. Furthermore, the introduction of new homologation cycles, such as the real driving emissions cycle, compels manufacturers to bridge the gap between engine operation in laboratory tests and real-world conditions. Within this context, this thesis showcases the performance and cost benefits achievable through the implementation of an auto-adaptive closed-loop control system, leveraging in-cylinder pressure sensors in a heavy-duty diesel engine designed for mining applications. Additionally, the thesis explores the promising prospect of real-time self-adaptive machine learning models, particularly neural networks, to develop an automatic system, using in-cylinder pressure sensors for the precise calibration of the target combustion phase and optimal spark advance in a spark-ignition engines. To facilitate the application of these combustion process feedback-based algorithms in production applications, the thesis discusses the results obtained from the development of a cost-effective sensor for indirect cylinder pressure measurement. Finally, to ensure the quality control of the proposed affordable sensor, the thesis provides a comprehensive account of the design and validation process for a piezoelectric washer test system.

Asymmetries in Adversarial Settings

Even without formal guarantees of their effectiveness, adversarial attacks against Machine Learning models frequently fool new defenses. We identify six key asymmetries that contribute to this phenomenon and formulate four guidelines to build future-proof defenses by preventing such asymmetries. We also prove that attacking a classifier is NP-complete, while defending from such attacks is Sigma_2^P-complete. We then introduce Counter-Attack (CA), an asymmetry-free metadefense that determines whether a model is robust on a given input by estimating its distance from the decision boundary. Under specific assumptions CA can provide theoretical detection guarantees. Additionally, we prove that while CA is NP-complete, fooling CA is Sigma_2^P-complete. Even when using heuristic relaxations, we show that our method can reliably identify non-robust points. As part of our experimental evaluation, we introduce UG100, a new dataset obtained by applying a provably optimal attack to six limited-scale networks (three for MNIST and three for CIFAR10), each trained in three different manners.

Hierarchical Multi-Label Text Classification in a Low-Resource Setting

In this thesis we address a multi-label hierarchical text classification problem in a low-resource setting and explore different approaches to identify the best one for our case. The goal is to train a model that classifies English school exercises according to a hierarchical taxonomy with few labeled data. The experiments made in this work employ different machine learning models and text representation techniques: CatBoost with tf-idf features, classifiers based on pre-trained models (mBERT, LASER), and SetFit, a framework for few-shot text classification. SetFit proved to be the most promising approach, achieving better performance when during training only a few labeled examples per class are available. However, this thesis does not consider all the hierarchical taxonomy, but only the first two levels: to address classification with the classes at the third level further experiments should be carried out, exploring methods for zero-shot text classification, data augmentation, and strategies to exploit the hierarchical structure of the taxonomy during training.

Copy-paste data augmentation for domain transfer on traffic signs

City streets carry a lot of information that can be exploited to improve the quality of the services the citizens receive. For example, autonomous vehicles need to act accordingly to all the element that are nearby the vehicle itself, like pedestrians, traffic signs and other vehicles. It is also possible to use such information for smart city applications, for example to predict and analyze the traffic or pedestrian flows. Among all the objects that it is possible to find in a street, traffic signs are very important because of the information they carry. This information can in fact be exploited both for autonomous driving and for smart city applications. Deep learning and, more generally, machine learning models however need huge quantities to learn. Even though modern models are very good at gener- alizing, the more samples the model has, the better it can generalize between different samples. Creating these datasets organically, namely with real pictures, is a very tedious task because of the wide variety of signs available in the whole world and especially because of all the possible light, orientation conditions and con- ditions in general in which they can appear. In addition to that, it may not be easy to collect enough samples for all the possible traffic signs available, cause some of them may be very rare to find. Instead of collecting pictures manually, it is possible to exploit data aug- mentation techniques to create synthetic datasets containing the signs that are needed. Creating this data synthetically allows to control the distribution and the conditions of the signs in the datasets, improving the quality and quantity of training data that is going to be used. This thesis work is about using copy-paste data augmentation to create synthetic data for the traffic sign recognition task.

Bayesian online algorithms for learning in discrete Hidden Markov Models

We propose and analyze two different Bayesian online algorithms for learning in discrete Hidden Markov Models and compare their performance with the already known Baldi-Chauvin Algorithm. Using the Kullback-Leibler divergence as a measure of generalization we draw learning curves in simplified situations for these algorithms and compare their performances.

Language policy spread: Learning from health and social policy models

Except for a few large scale projects, language planners have tended to talk and argue among themselves rather than to see language policy development as an inherently political process. A comparison with a social policy example, taken from the United States, suggests that it is important to understand the problem and to develop solutions in the context of the political process, as this is where decisions will ultimately be made.

A Feedback Learning and Mental Models Perspective on Strategic Decision Making

This study aims to be a contribution to a theoretical model that explains the effectiveness of the learning and decision-making processes by means of a feedback and mental models perspective. With appropriate mental models, managers should be able to improve their capacity to deal with dynamically complex contexts, in order to achieve long-term success. We present a set of hypotheses about the influence of feedback information and systems thinking facilitation on mental models and management performance. We explore, under controlled conditions, the role of mental models in terms of structure and behaviour. A test based on a simulation experiment with a system dynamics model was performed. Three out of the four hypotheses were confirmed. Causal diagramming positively influences mental model structure similarity, mental model structure similarity positively influences mental model behaviour similarity, and mental model behaviour similarity positively influences the quality of the decision.

A Feedback Learning and Mental Models Perspective on Strategic Decision Making

This study aims to be a contribution to a theoretical model that explains the effectiveness of the learning and decision-making processes by means of a feedback and mental models perspective. With appropriate mental models, managers should be able to improve their capacity to deal with dynamically complex contexts, in order to achieve long-term success. We present a set of hypotheses about the influence of feedback information and systems thinking facilitation on mental models and management performance. We explore, under controlled conditions, the role of mental models in terms of structure and behaviour. A test based on a simulation experiment with a system dynamics model was performed. Three out of the four hypotheses were confirmed. Causal diagramming positively influences mental model structure similarity, mental model structure similarity positively influences mental model behaviour similarity, and mental model behaviour similarity positively influences the quality of the decision

Learning facial-expression models with crowdsourcing

The computational power is increasing day by day. Despite that, there are some tasks that are still difficult or even impossible for a computer to perform. For example, while identifying a facial expression is easy for a human, for a computer it is an area in development. To tackle this and similar issues, crowdsourcing has grown as a way to use human computation in a large scale. Crowdsourcing is a novel approach to collect labels in a fast and cheap manner, by sourcing the labels from the crowds. However, these labels lack reliability since annotators are not guaranteed to have any expertise in the field. This fact has led to a new research area where we must create or adapt annotation models to handle these weaklylabeled data. Current techniques explore the annotators’ expertise and the task difficulty as variables that influences labels’ correction. Other specific aspects are also considered by noisy-labels analysis techniques. The main contribution of this thesis is the process to collect reliable crowdsourcing labels for a facial expressions dataset. This process consists in two steps: first, we design our crowdsourcing tasks to collect annotators labels; next, we infer the true label from the collected labels by applying state-of-art crowdsourcing algorithms. At the same time, a facial expression dataset is created, containing 40.000 images and respective labels. At the end, we publish the resulting dataset.

Two-sided learning in new keynesian models: dynamics, (lack of) convergence and the value of information

This paper investigates the role of learning by private agents and the central bank (two-sided learning) in a New Keynesian framework in which both sides of the economy have asymmetric and imperfect knowledge about the true data generating process. We assume that all agents employ the data that they observe (which may be distinct for different sets of agents) to form beliefs about unknown aspects of the true model of the economy, use their beliefs to decide on actions, and revise these beliefs through a statistical learning algorithm as new information becomes available. We study the short-run dynamics of our model and derive its policy recommendations, particularly with respect to central bank communications. We demonstrate that two-sided learning can generate substantial increases in volatility and persistence, and alter the behavior of the variables in the model in a signifficant way. Our simulations do not converge to a symmetric rational expectations equilibrium and we highlight one source that invalidates the convergence results of Marcet and Sargent (1989). Finally, we identify a novel aspect of central bank communication in models of learning: communication can be harmful if the central bank's model is substantially mis-specified