Exploration des réseaux de neurones à base d'autoencodeur dans le cadre de la modélisation des données textuelles

Depuis le milieu des années 2000, une nouvelle approche en apprentissage automatique, l'apprentissage de réseaux profonds (deep learning), gagne en popularité. En effet, cette approche a démontré son efficacité pour résoudre divers problèmes en améliorant les résultats obtenus par d'autres techniques qui étaient considérées alors comme étant l'état de l'art. C'est le cas pour le domaine de la reconnaissance d'objets ainsi que pour la reconnaissance de la parole. Sachant cela, l’utilisation des réseaux profonds dans le domaine du Traitement Automatique du Langage Naturel (TALN, Natural Language Processing) est donc une étape logique à suivre. Cette thèse explore différentes structures de réseaux de neurones dans le but de modéliser le texte écrit, se concentrant sur des modèles simples, puissants et rapides à entraîner.

Mutual Information-based RBM Neural Networks

(Deep) neural networks are increasingly being used for various computer vision and pattern recognition tasks due to their strong ability to learn highly discriminative features. However, quantitative analysis of their classication ability and design philosophies are still nebulous. In this work, we use information theory to analyze the concatenated restricted Boltzmann machines (RBMs) and propose a mutual information-based RBM neural networks (MI-RBM). We develop a novel pretraining algorithm to maximize the mutual information between RBMs. Extensive experimental results on various classication tasks show the eectiveness of the proposed approach.

Análisis predictivo para clasificar dígitos escritos a mano utilizando la base de datos MNIST

En el presente trabajo de fin de máster se realiza una investigación sobre las técnicas de preproceso del dataset de entrenamiento y la aplicación de un modelo de predicción que realice una clasificación de dı́gitos escritos a mano. El conjunto de dataset de train y test son proporcionado en la competencia de Kaggle: Digit Recognizer y provienen de la base de datos de dı́gitos manuscritos MNIST. Por tratarse de imágenes las técnicas de preproceso se concentran en obtener una imagen lo más nı́tida posible y la reducción de tamaño de la misma, objetivos que se logran con técnicas de umbralización por el método de Otsu, transformada de Wavelet de Haar y el análisis de sus componentes principales. Se utiliza Deep Learning como modelo predictivo por ajustarse a este tipo de datos, se emplean además librerı́as de código abierto implementadas en el lenguaje estádisto R. Por último se obtiene una predicción con las técnicas y herramientas mencio- nadas para ser evaluada en la competencia de Kaggle, midiendo y comparando los resultados obtenidos con el resto de participantes.

Detection and Grading of Prostate Cancer in Temporal Enhanced Ultrasound using Convolutional Neural Networks

Prostate cancer is the most common non-dermatological cancer amongst men in the developed world. The current definitive diagnosis is core needle biopsy guided by transrectal ultrasound. However, this method suffers from low sensitivity and specificity in detecting cancer. Recently, a new ultrasound based tissue typing approach has been proposed, known as temporal enhanced ultrasound (TeUS). In this approach, a set of temporal ultrasound frames is collected from a stationary tissue location without any intentional mechanical excitation. The main aim of this thesis is to implement a deep learning-based solution for prostate cancer detection and grading using TeUS data. In the proposed solution, convolutional neural networks are trained to extract high-level features from time domain TeUS data in temporally and spatially adjacent frames in nine in vivo prostatectomy cases. This approach avoids information loss due to feature extraction and also improves cancer detection rate. The output likelihoods of two TeUS arrangements are then combined to form our novel decision support system. This deep learning-based approach results in the area under the receiver operating characteristic curve (AUC) of 0.80 and 0.73 for prostate cancer detection and grading, respectively, in leave-one-patient-out cross-validation. Recently, multi-parametric magnetic resonance imaging (mp-MRI) has been utilized to improve detection rate of aggressive prostate cancer. In this thesis, for the first time, we present the fusion of mp-MRI and TeUS for characterization of prostate cancer to compensates the deficiencies of each image modalities and improve cancer detection rate. The results obtained using TeUS are fused with those attained using consolidated mp-MRI maps from multiple MR modalities and cancer delineations on those by multiple clinicians. The proposed fusion approach yields the AUC of 0.86 in prostate cancer detection. The outcomes of this thesis emphasize the viable potential of TeUS as a tissue typing method. Employing this ultrasound-based intervention, which is non-invasive and inexpensive, can be a valuable and practical addition to enhance the current prostate cancer detection.

Journalisation dans un Programme de carrière en nouveaux médias : Le rôle de la réflexion par l’action

The purpose of this case study is to report on the use of learning journals as a strategy to encourage critical reflection in the field of graphic design. Very little empirical research has been published regarding the use of critical reflection in learning journals in this field. Furthermore, nothing has been documented at the college level. To that end, the goal of this research endeavor was to investigate whether second-year students in the NewMedia and Publication Design Program at a small Anglophone CEGEP in Québec, enrolled in a Page Layout and Design course, learn more deeply by reflecting in action during design projects or reflecting on action after completing design projects. Secondarily, indications of a possible change in self-efficacy were examined. Two hypotheses were posited: 1) reflection-on-action journaling will promote a deeper approach to learning than reflection-in-action journaling, and 2) the level of self-efficacy in graphic design improves as students are encouraged to think reflectively. Using both qualitative and quantitative methods, a mixed methods approach was used to collect and analyze the data. Content analysis of journal entries and interview responses was the primary method used to address the first hypothesis. Students were required to journal twice for each of three projects, once during the project and again one week after the project had been submitted. In addition, data regarding the students' perception of journaling was obtained through administering a survey and conducting interviews. For the second hypothesis, quantitative methods were used through the use of two surveys, one administered early in the Fall 2011 semester and the second administered early in the Winter 2012 semester. Supplementary data regarding self-efficacy was obtained in the form of content analysis of journal entries and interviews. Coded journal entries firmly supported the hypothesis that reflection-on-action journaling promotes deep learning. Using a taxonomy developed by Kember et al. (1999) wherein "critical reflection" is considered the highest level of reflection, it was found that only 5% of the coded responses in the reflection-in-action journals were deemed of the highest level, whereas 39% were considered critical reflection in the reflection-on-action journals. The findings from the interviews suggest that students had some initial concerns about the value of journaling, but these concerns were later dismissed as students learned that journaling was a valuable tool that helped them reflect and learn. All participants indicated that journaling changed their learning processes as they thought much more about what they were doing while they were doing it. They were taking the learning they had acquired and thinking about how they would apply it to new projects; this is critical reflection. The survey findings did not support the conclusive results of the comparison of journal instruments, where an increase of 35% in critical reflection was noted in the reflection-on-action journals. In Chapter 5, reasons for this incongruence are explored. Furthermore, based on the journals, surveys, and interviews, there is not enough evidence at this time to support the hypothesis that self-efficacy improves when students are encouraged to think reflectively. It could be hypothesized, however, that one's self-efficacy does not change in such a short period of time. In conclusion, the findings established in this case study make a practical contribution to the literature concerning the promotion of deep learning in the field of graphic design, as this researcher's hypothesis was supported that reflection-on-action journaling promoted deeper learning than reflection-in-action journaling. When examining the increases in critical reflection from reflection-in-action to the reflection-on-action journals, it was found that all students but one showed an increase in critical reflection in reflection-on-action journals. It is therefore recommended that production-oriented program instructors consider integrating reflection-on-action journaling into their courses where projects are given.

Automotive Radars:towards smarter vehicles

Radars are expected to become the main sensors in various civilian applications, especially for autonomous driving. Their success is mainly due to the availability of low cost integrated devices, equipped with compact antenna arrays, and computationally efficient signal processing techniques. This thesis focuses on the study and the development of different deterministic and learning based techniques for colocated multiple-input multiple-output (MIMO) radars. In particular, after providing an overview on the architecture of these devices, the problem of detecting and estimating multiple targets in stepped frequency continuous wave (SFCW) MIMO radar systems is investigated and different deterministic techniques solving it are illustrated. Moreover, novel solutions, based on an approximate maximum likelihood approach, are developed. The accuracy achieved by all the considered algorithms is assessed on the basis of the raw data acquired from low power wideband radar devices. The results demonstrate that the developed algorithms achieve reasonable accuracies, but at the price of different computational efforts. Another important technical problem investigated in this thesis concerns the exploitation of machine learning and deep learning techniques in the field of colocated MIMO radars. In this thesis, after providing a comprehensive overview of the machine learning and deep learning techniques currently being considered for use in MIMO radar systems, their performance in two different applications is assessed on the basis of synthetically generated and experimental datasets acquired through a commercial frequency modulated continuous wave (FMCW) MIMO radar. Finally, the application of colocated MIMO radars to autonomous driving in smart agriculture is illustrated.

Exact Combinatorial Optimization with Graph Convolutional Neural Networks

Combinatorial optimization problems are typically tackled by the branch-and-bound paradigm. We propose to learn a variable selection policy for branch-and-bound in mixed-integer linear programming, by imitation learning on a diversified variant of the strong branching expert rule. We encode states as bipartite graphs and parameterize the policy as a graph convolutional neural network. Experiments on a series of synthetic problems demonstrate that our approach produces policies that can improve upon expert-designed branching rules on large problems, and generalize to instances significantly larger than seen during training.

Sperimentazione e confronto di soluzioni per il rilevamento della mascherina sanitaria facciale

L’obiettivo principale della tesi, è quello di mettere a confronto soluzioni basate su tecnologie diverse e individuare la soluzione migliore che permetta di stabilire se le persone inquadrate in un’immagine indossano correttamente o meno la mascherina protettiva come previsto dalle norme anti-covid. Per raggiungere l’obiettivo verranno confrontate diverse architetture costruite per lo stesso scopo e che si basano sui principi di Machine Learning e Deep Learning, e verranno messe in funzione su insieme di dataset individuati, che sono stati creati per propositi affini.

Automatic detection of the inferior alveolar nerve in CT scans with CenterNet

The inferior alveolar nerve (IAN) lies within the mandibular canal, named inferior alveolar canal in literature. The detection of this nerve is important during maxillofacial surgeries or for creating dental implants. The poor quality of cone-beam computed tomography (CBCT) and computed tomography (CT) scans and/or bone gaps within the mandible increase the difficulty of this task, posing a challenge to human experts who are going to manually detect it and resulting in a time-consuming task.Therefore this thesis investigates two methods to automatically detect the IAN: a non-data driven technique and a deep-learning method. The latter tracks the IAN position at each frame leveraging detections obtained with the deep neural network CenterNet, fined-tuned for our task, and temporal and spatial information.

Monitoring and Prediction of Thermal Emergencies in High Performance Computing Systems

Modern scientific discoveries are driven by an unsatisfiable demand for computational resources. High-Performance Computing (HPC) systems are an aggregation of computing power to deliver considerably higher performance than one typical desktop computer can provide, to solve large problems in science, engineering, or business. An HPC room in the datacenter is a complex controlled environment that hosts thousands of computing nodes that consume electrical power in the range of megawatts, which gets completely transformed into heat. Although a datacenter contains sophisticated cooling systems, our studies indicate quantitative evidence of thermal bottlenecks in real-life production workload, showing the presence of significant spatial and temporal thermal and power heterogeneity. Therefore minor thermal issues/anomalies can potentially start a chain of events that leads to an unbalance between the amount of heat generated by the computing nodes and the heat removed by the cooling system originating thermal hazards. Although thermal anomalies are rare events, anomaly detection/prediction in time is vital to avoid IT and facility equipment damage and outage of the datacenter, with severe societal and business losses. For this reason, automated approaches to detect thermal anomalies in datacenters have considerable potential. This thesis analyzed and characterized the power and thermal characteristics of a Tier0 datacenter (CINECA) during production and under abnormal thermal conditions. Then, a Deep Learning (DL)-powered thermal hazard prediction framework is proposed. The proposed models are validated against real thermal hazard events reported for the studied HPC cluster while in production. This thesis is the first empirical study of thermal anomaly detection and prediction techniques of a real large-scale HPC system to the best of my knowledge. For this thesis, I used a large-scale dataset, monitoring data of tens of thousands of sensors for around 24 months with a data collection rate of around 20 seconds.

Perceiving the 3d world from single images

Depth represents a crucial piece of information in many practical applications, such as obstacle avoidance and environment mapping. This information can be provided either by active sensors, such as LiDARs, or by passive devices like cameras. A popular passive device is the binocular rig, which allows triangulating the depth of the scene through two synchronized and aligned cameras. However, many devices that are already available in several infrastructures are monocular passive sensors, such as most of the surveillance cameras. The intrinsic ambiguity of the problem makes monocular depth estimation a challenging task. Nevertheless, the recent progress of deep learning strategies is paving the way towards a new class of algorithms able to handle this complexity. This work addresses many relevant topics related to the monocular depth estimation problem. It presents networks capable of predicting accurate depth values even on embedded devices and without the need of expensive ground-truth labels at training time. Moreover, it introduces strategies to estimate the uncertainty of these models, and it shows that monocular networks can easily generate training labels for different tasks at scale. Finally, it evaluates off-the-shelf monocular depth predictors for the relevant use case of social distance monitoring, and shows how this technology allows to overcome already existing strategies limitations.

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.

Interpretable Convolutional Neural Networks for Decoding and Analyzing Neural Time Series Data

Machine learning is widely adopted to decode multi-variate neural time series, including electroencephalographic (EEG) and single-cell recordings. Recent solutions based on deep learning (DL) outperformed traditional decoders by automatically extracting relevant discriminative features from raw or minimally pre-processed signals. Convolutional Neural Networks (CNNs) have been successfully applied to EEG and are the most common DL-based EEG decoders in the state-of-the-art (SOA). However, the current research is affected by some limitations. SOA CNNs for EEG decoding usually exploit deep and heavy structures with the risk of overfitting small datasets, and architectures are often defined empirically. Furthermore, CNNs are mainly validated by designing within-subject decoders. Crucially, the automatically learned features mainly remain unexplored; conversely, interpreting these features may be of great value to use decoders also as analysis tools, highlighting neural signatures underlying the different decoded brain or behavioral states in a data-driven way. Lastly, SOA DL-based algorithms used to decode single-cell recordings rely on more complex, slower to train and less interpretable networks than CNNs, and the use of CNNs with these signals has not been investigated. This PhD research addresses the previous limitations, with reference to P300 and motor decoding from EEG, and motor decoding from single-neuron activity. CNNs were designed light, compact, and interpretable. Moreover, multiple training strategies were adopted, including transfer learning, which could reduce training times promoting the application of CNNs in practice. Furthermore, CNN-based EEG analyses were proposed to study neural features in the spatial, temporal and frequency domains, and proved to better highlight and enhance relevant neural features related to P300 and motor states than canonical EEG analyses. Remarkably, these analyses could be used, in perspective, to design novel EEG biomarkers for neurological or neurodevelopmental disorders. Lastly, CNNs were developed to decode single-neuron activity, providing a better compromise between performance and model complexity.

Big Data approaches as a support for precision livestock farming techniques

With the advent of new technologies it is increasingly easier to find data of different nature from even more accurate sensors that measure the most disparate physical quantities and with different methodologies. The collection of data thus becomes progressively important and takes the form of archiving, cataloging and online and offline consultation of information. Over time, the amount of data collected can become so relevant that it contains information that cannot be easily explored manually or with basic statistical techniques. The use of Big Data therefore becomes the object of more advanced investigation techniques, such as Machine Learning and Deep Learning. In this work some applications in the world of precision zootechnics and heat stress accused by dairy cows are described. Experimental Italian and German stables were involved for the training and testing of the Random Forest algorithm, obtaining a prediction of milk production depending on the microclimatic conditions of the previous days with satisfactory accuracy. Furthermore, in order to identify an objective method for identifying production drops, compared to the Wood model, typically used as an analytical model of the lactation curve, a Robust Statistics technique was used. Its application on some sample lactations and the results obtained allow us to be confident about the use of this method in the future.