Rich media content adaptation in e-learning systems

The wide use of e-technologies represents a great opportunity for underserved segments of the population, especially with the aim of reintegrating excluded individuals back into society through education. This is particularly true for people with different types of disabilities who may have difficulties while attending traditional on-site learning programs that are typically based on printed learning resources. The creation and provision of accessible e-learning contents may therefore become a key factor in enabling people with different access needs to enjoy quality learning experiences and services. Another e-learning challenge is represented by m-learning (which stands for mobile learning), which is emerging as a consequence of mobile terminals diffusion and provides the opportunity to browse didactical materials everywhere, outside places that are traditionally devoted to education. Both such situations share the need to access materials in limited conditions and collide with the growing use of rich media in didactical contents, which are designed to be enjoyed without any restriction. Nowadays, Web-based teaching makes great use of multimedia technologies, ranging from Flash animations to prerecorded video-lectures. Rich media in e-learning can offer significant potential in enhancing the learning environment, through helping to increase access to education, enhance the learning experience and support multiple learning styles. Moreover, they can often be used to improve the structure of Web-based courses. These highly variegated and structured contents may significantly improve the quality and the effectiveness of educational activities for learners. For example, rich media contents allow us to describe complex concepts and process flows. Audio and video elements may be utilized to add a “human touch” to distance-learning courses. Finally, real lectures may be recorded and distributed to integrate or enrich on line materials. A confirmation of the advantages of these approaches can be seen in the exponential growth of video-lecture availability on the net, due to the ease of recording and delivering activities which take place in a traditional classroom. Furthermore, the wide use of assistive technologies for learners with disabilities injects new life into e-learning systems. E-learning allows distance and flexible educational activities, thus helping disabled learners to access resources which would otherwise present significant barriers for them. For instance, students with visual impairments have difficulties in reading traditional visual materials, deaf learners have trouble in following traditional (spoken) lectures, people with motion disabilities have problems in attending on-site programs. As already mentioned, the use of wireless technologies and pervasive computing may really enhance the educational learner experience by offering mobile e-learning services that can be accessed by handheld devices. This new paradigm of educational content distribution maximizes the benefits for learners since it enables users to overcome constraints imposed by the surrounding environment. While certainly helpful for users without disabilities, we believe that the use of newmobile technologies may also become a fundamental tool for impaired learners, since it frees them from sitting in front of a PC. In this way, educational activities can be enjoyed by all the users, without hindrance, thus increasing the social inclusion of non-typical learners. While the provision of fully accessible and portable video-lectures may be extremely useful for students, it is widely recognized that structuring and managing rich media contents for mobile learning services are complex and expensive tasks. Indeed, major difficulties originate from the basic need to provide a textual equivalent for each media resource composing a rich media Learning Object (LO). Moreover, tests need to be carried out to establish whether a given LO is fully accessible to all kinds of learners. Unfortunately, both these tasks are truly time-consuming processes, depending on the type of contents the teacher is writing and on the authoring tool he/she is using. Due to these difficulties, online LOs are often distributed as partially accessible or totally inaccessible content. Bearing this in mind, this thesis aims to discuss the key issues of a system we have developed to deliver accessible, customized or nomadic learning experiences to learners with different access needs and skills. To reduce the risk of excluding users with particular access capabilities, our system exploits Learning Objects (LOs) which are dynamically adapted and transcoded based on the specific needs of non-typical users and on the barriers that they can encounter in the environment. The basic idea is to dynamically adapt contents, by selecting them from a set of media resources packaged in SCORM-compliant LOs and stored in a self-adapting format. The system schedules and orchestrates a set of transcoding processes based on specific learner needs, so as to produce a customized LO that can be fully enjoyed by any (impaired or mobile) student.

Formazione, apprendimento e nuove prospettive e-learning. Lo sviluppo delle nuove tecnologie didattiche e la creazione di sistemi di apprendimento lungo l’intero arco della vita

The thesis of this paper is based on the assumption that the socio-economic system in which we are living is characterised by three great trends: growing attention to the promotion of human capital; extremely rapid technological progress, based above all on the information and communication technologies (ICT); the establishment of new production and organizational set-ups. These transformation processes pose a concrete challenge to the training sector, which is called to satisfy the demand for new skills that need to be developed and disseminated. Hence the growing interest that the various training sub-systems devote to the issues of lifelong learning and distance learning. In such a context, the so-called e-learning acquires a central role. The first chapter proposes a reference theoretical framework for the transformations that are shaping post-industrial society. It analyzes some key issues such as: how work is changing, the evolution of organizational set-ups and the introduction of learning organization, the advent of the knowledge society and of knowledge companies, the innovation of training processes, and the key role of ICT in the new training and learning systems. The second chapter focuses on the topic of e-learning as an effective training model in response to the need for constant learning that is emerging in the knowledge society. This chapter starts with a reflection on the importance of lifelong learning and introduces the key arguments of this thesis, i.e. distance learning (DL) and the didactic methodology called e-learning. It goes on with an analysis of the various theoretic and technical aspects of e-learning. In particular, it delves into the theme of e-learning as an integrated and constant training environment, characterized by customized programmes and collaborative learning, didactic assistance and constant monitoring of the results. Thus, all the aspects of e-learning are taken into exam: the actors and the new professionals, the virtual communities as learning subjects, the organization of contents in learning objects, the conformity to international standards, the integrated platforms and so on. The third chapter, which concludes the theoretic-interpretative part, starts with a short presentation of the state-of-the-art e-learning international market that aims to understand its peculiarities and its current trends. Finally, we focus on some important regulation aspects related to the strong impulse given by the European Commission first, and by the Italian governments secondly, to the development and diffusion of e-learning. The second part of the thesis (chapters 4, 5 and 6) focus on field research, which aims to define the Italian scenario for e-learning. In particular, we have examined some key topics such as: the challenges of training and the instruments to face such challenges; the new didactic methods and technologies for lifelong learning; the level of diffusion of e-learning in Italy; the relation between classroom training and online training; the main factors of success as well as the most critical aspects of the introduction of e-learning in the various learning environments. As far as the methodological aspects are concerned, we have favoured a qualitative and quantitative analysis. A background analysis has been done to collect the statistical data available on this topic, as well as the research previously carried out in this area. The main source of data is constituted by the results of the Observatory on e-learning of Aitech-Assinform, which covers the 2000s and four areas of implementation (firms, public administration, universities, school): the thesis has reviewed the results of the last three available surveys, offering a comparative interpretation of them. We have then carried out an in-depth empirical examination of two case studies, which have been selected by virtue of the excellence they have achieved and can therefore be considered advanced and emblematic experiences (a large firm and a Graduate School).

Concepts and methods for efficient decentralized learning in federated settings

Deep Neural Networks (DNNs) have revolutionized a wide range of applications beyond traditional machine learning and artificial intelligence fields, e.g., computer vision, healthcare, natural language processing and others. At the same time, edge devices have become central in our society, generating an unprecedented amount of data which could be used to train data-hungry models such as DNNs. However, the potentially sensitive or confidential nature of gathered data poses privacy concerns when storing and processing them in centralized locations. To this purpose, decentralized learning decouples model training from the need of directly accessing raw data, by alternating on-device training and periodic communications. The ability of distilling knowledge from decentralized data, however, comes at the cost of facing more challenging learning settings, such as coping with heterogeneous hardware and network connectivity, statistical diversity of data, and ensuring verifiable privacy guarantees. This Thesis proposes an extensive overview of decentralized learning literature, including a novel taxonomy and a detailed description of the most relevant system-level contributions in the related literature for privacy, communication efficiency, data and system heterogeneity, and poisoning defense. Next, this Thesis presents the design of an original solution to tackle communication efficiency and system heterogeneity, and empirically evaluates it on federated settings. For communication efficiency, an original method, specifically designed for Convolutional Neural Networks, is also described and evaluated against the state-of-the-art. Furthermore, this Thesis provides an in-depth review of recently proposed methods to tackle the performance degradation introduced by data heterogeneity, followed by empirical evaluations on challenging data distributions, highlighting strengths and possible weaknesses of the considered solutions. Finally, this Thesis presents a novel perspective on the usage of Knowledge Distillation as a mean for optimizing decentralized learning systems in settings characterized by data heterogeneity or system heterogeneity. Our vision on relevant future research directions close the manuscript.

Integrated communication and learning towards autonomous mobile radio networks

The integration of distributed and ubiquitous intelligence has emerged over the last years as the mainspring of transformative advancements in mobile radio networks. As we approach the era of “mobile for intelligence”, next-generation wireless networks are poised to undergo significant and profound changes. Notably, the overarching challenge that lies ahead is the development and implementation of integrated communication and learning mechanisms that will enable the realization of autonomous mobile radio networks. The ultimate pursuit of eliminating human-in-the-loop constitutes an ambitious challenge, necessitating a meticulous delineation of the fundamental characteristics that artificial intelligence (AI) should possess to effectively achieve this objective. This challenge represents a paradigm shift in the design, deployment, and operation of wireless networks, where conventional, static configurations give way to dynamic, adaptive, and AI-native systems capable of self-optimization, self-sustainment, and learning. This thesis aims to provide a comprehensive exploration of the fundamental principles and practical approaches required to create autonomous mobile radio networks that seamlessly integrate communication and learning components. The first chapter of this thesis introduces the notion of Predictive Quality of Service (PQoS) and adaptive optimization and expands upon the challenge to achieve adaptable, reliable, and robust network performance in dynamic and ever-changing environments. The subsequent chapter delves into the revolutionary role of generative AI in shaping next-generation autonomous networks. This chapter emphasizes achieving trustworthy uncertainty-aware generation processes with the use of approximate Bayesian methods and aims to show how generative AI can improve generalization while reducing data communication costs. Finally, the thesis embarks on the topic of distributed learning over wireless networks. Distributed learning and its declinations, including multi-agent reinforcement learning systems and federated learning, have the potential to meet the scalability demands of modern data-driven applications, enabling efficient and collaborative model training across dynamic scenarios while ensuring data privacy and reducing communication overhead.

Learning representations for graph-structured socio-technical systems

The recent widespread use of social media platforms and web services has led to a vast amount of behavioral data that can be used to model socio-technical systems. A significant part of this data can be represented as graphs or networks, which have become the prevalent mathematical framework for studying the structure and the dynamics of complex interacting systems. However, analyzing and understanding these data presents new challenges due to their increasing complexity and diversity. For instance, the characterization of real-world networks includes the need of accounting for their temporal dimension, together with incorporating higher-order interactions beyond the traditional pairwise formalism. The ongoing growth of AI has led to the integration of traditional graph mining techniques with representation learning and low-dimensional embeddings of networks to address current challenges. These methods capture the underlying similarities and geometry of graph-shaped data, generating latent representations that enable the resolution of various tasks, such as link prediction, node classification, and graph clustering. As these techniques gain popularity, there is even a growing concern about their responsible use. In particular, there has been an increased emphasis on addressing the limitations of interpretability in graph representation learning. This thesis contributes to the advancement of knowledge in the field of graph representation learning and has potential applications in a wide range of complex systems domains. We initially focus on forecasting problems related to face-to-face contact networks with time-varying graph embeddings. Then, we study hyperedge prediction and reconstruction with simplicial complex embeddings. Finally, we analyze the problem of interpreting latent dimensions in node embeddings for graphs. The proposed models are extensively evaluated in multiple experimental settings and the results demonstrate their effectiveness and reliability, achieving state-of-the-art performances and providing valuable insights into the properties of the learned representations.

Directly training spiking neural networks for cyber-physical systems: from supervised to reinforcement learning

Spiking Neural Networks (SNNs) are bio-inspired Artificial Neural Networks (ANNs) utilizing discrete spiking signals, akin to neuron communication in the brain, making them ideal for real-time and energy-efficient Cyber-Physical Systems (CPSs). This thesis explores their potential in Structural Health Monitoring (SHM), leveraging low-cost MEMS accelerometers for early damage detection in motorway bridges. The study focuses on Long Short-Term SNNs (LSNNs), although their complex learning processes pose challenges. Comparing LSNNs with other ANN models and training algorithms for SHM, findings indicate LSNNs' effectiveness in damage identification, comparable to ANNs trained using traditional methods. Additionally, an optimized embedded LSNN implementation demonstrates a 54% reduction in execution time, but with longer pre-processing due to spike-based encoding. Furthermore, SNNs are applied in UAV obstacle avoidance, trained directly using a Reinforcement Learning (RL) algorithm with event-based input from a Dynamic Vision Sensor (DVS). Performance evaluation against Convolutional Neural Networks (CNNs) highlights SNNs' superior energy efficiency, showing a 6x decrease in energy consumption. The study also investigates embedded SNN implementations' latency and throughput in real-world deployments, emphasizing their potential for energy-efficient monitoring systems. This research contributes to advancing SHM and UAV obstacle avoidance through SNNs' efficient information processing and decision-making capabilities within CPS domains.

Knowledge management in intelligent tutoring systems

In the last years, Intelligent Tutoring Systems have been a very successful way for improving learning experience. Many issues must be addressed until this technology can be defined mature. One of the main problems within the Intelligent Tutoring Systems is the process of contents authoring: knowledge acquisition and manipulation processes are difficult tasks because they require a specialised skills on computer programming and knowledge engineering. In this thesis we discuss a general framework for knowledge management in an Intelligent Tutoring System and propose a mechanism based on first order data mining to partially automate the process of knowledge acquisition that have to be used in the ITS during the tutoring process. Such a mechanism can be applied in Constraint Based Tutor and in the Pseudo-Cognitive Tutor. We design and implement a part of the proposed architecture, mainly the module of knowledge acquisition from examples based on first order data mining. We then show that the algorithm can be applied at least two different domains: first order algebra equation and some topics of C programming language. Finally we discuss the limitation of current approach and the possible improvements of the whole framework.

Development of Clinical Decision Support Systems based on Mathematical Models of Physiological Systems

In the last years of research, I focused my studies on different physiological problems. Together with my supervisors, I developed/improved different mathematical models in order to create valid tools useful for a better understanding of important clinical issues. The aim of all this work is to develop tools for learning and understanding cardiac and cerebrovascular physiology as well as pathology, generating research questions and developing clinical decision support systems useful for intensive care unit patients. I. ICP-model Designed for Medical Education We developed a comprehensive cerebral blood flow and intracranial pressure model to simulate and study the complex interactions in cerebrovascular dynamics caused by multiple simultaneous alterations, including normal and abnormal functional states of auto-regulation of the brain. Individual published equations (derived from prior animal and human studies) were implemented into a comprehensive simulation program. Included in the normal physiological modelling was: intracranial pressure, cerebral blood flow, blood pressure, and carbon dioxide (CO2) partial pressure. We also added external and pathological perturbations, such as head up position and intracranial haemorrhage. The model performed clinically realistically given inputs of published traumatized patients, and cases encountered by clinicians. The pulsatile nature of the output graphics was easy for clinicians to interpret. The manoeuvres simulated include changes of basic physiological inputs (e.g. blood pressure, central venous pressure, CO2 tension, head up position, and respiratory effects on vascular pressures) as well as pathological inputs (e.g. acute intracranial bleeding, and obstruction of cerebrospinal outflow). Based on the results, we believe the model would be useful to teach complex relationships of brain haemodynamics and study clinical research questions such as the optimal head-up position, the effects of intracranial haemorrhage on cerebral haemodynamics, as well as the best CO2 concentration to reach the optimal compromise between intracranial pressure and perfusion. We believe this model would be useful for both beginners and advanced learners. It could be used by practicing clinicians to model individual patients (entering the effects of needed clinical manipulations, and then running the model to test for optimal combinations of therapeutic manoeuvres). II. A Heterogeneous Cerebrovascular Mathematical Model Cerebrovascular pathologies are extremely complex, due to the multitude of factors acting simultaneously on cerebral haemodynamics. In this work, the mathematical model of cerebral haemodynamics and intracranial pressure dynamics, described in the point I, is extended to account for heterogeneity in cerebral blood flow. The model includes the Circle of Willis, six regional districts independently regulated by autoregulation and CO2 reactivity, distal cortical anastomoses, venous circulation, the cerebrospinal fluid circulation, and the intracranial pressure-volume relationship. Results agree with data in the literature and highlight the existence of a monotonic relationship between transient hyperemic response and the autoregulation gain. During unilateral internal carotid artery stenosis, local blood flow regulation is progressively lost in the ipsilateral territory with the presence of a steal phenomenon, while the anterior communicating artery plays the major role to redistribute the available blood flow. Conversely, distal collateral circulation plays a major role during unilateral occlusion of the middle cerebral artery. In conclusion, the model is able to reproduce several different pathological conditions characterized by heterogeneity in cerebrovascular haemodynamics and can not only explain generalized results in terms of physiological mechanisms involved, but also, by individualizing parameters, may represent a valuable tool to help with difficult clinical decisions. III. Effect of Cushing Response on Systemic Arterial Pressure. During cerebral hypoxic conditions, the sympathetic system causes an increase in arterial pressure (Cushing response), creating a link between the cerebral and the systemic circulation. This work investigates the complex relationships among cerebrovascular dynamics, intracranial pressure, Cushing response, and short-term systemic regulation, during plateau waves, by means of an original mathematical model. The model incorporates the pulsating heart, the pulmonary circulation and the systemic circulation, with an accurate description of the cerebral circulation and the intracranial pressure dynamics (same model as in the first paragraph). Various regulatory mechanisms are included: cerebral autoregulation, local blood flow control by oxygen (O2) and/or CO2 changes, sympathetic and vagal regulation of cardiovascular parameters by several reflex mechanisms (chemoreceptors, lung-stretch receptors, baroreceptors). The Cushing response has been described assuming a dramatic increase in sympathetic activity to vessels during a fall in brain O2 delivery. With this assumption, the model is able to simulate the cardiovascular effects experimentally observed when intracranial pressure is artificially elevated and maintained at constant level (arterial pressure increase and bradicardia). According to the model, these effects arise from the interaction between the Cushing response and the baroreflex response (secondary to arterial pressure increase). Then, patients with severe head injury have been simulated by reducing intracranial compliance and cerebrospinal fluid reabsorption. With these changes, oscillations with plateau waves developed. In these conditions, model results indicate that the Cushing response may have both positive effects, reducing the duration of the plateau phase via an increase in cerebral perfusion pressure, and negative effects, increasing the intracranial pressure plateau level, with a risk of greater compression of the cerebral vessels. This model may be of value to assist clinicians in finding the balance between clinical benefits of the Cushing response and its shortcomings. IV. Comprehensive Cardiopulmonary Simulation Model for the Analysis of Hypercapnic Respiratory Failure We developed a new comprehensive cardiopulmonary model that takes into account the mutual interactions between the cardiovascular and the respiratory systems along with their short-term regulatory mechanisms. The model includes the heart, systemic and pulmonary circulations, lung mechanics, gas exchange and transport equations, and cardio-ventilatory control. Results show good agreement with published patient data in case of normoxic and hyperoxic hypercapnia simulations. In particular, simulations predict a moderate increase in mean systemic arterial pressure and heart rate, with almost no change in cardiac output, paralleled by a relevant increase in minute ventilation, tidal volume and respiratory rate. The model can represent a valid tool for clinical practice and medical research, providing an alternative way to experience-based clinical decisions. In conclusion, models are not only capable of summarizing current knowledge, but also identifying missing knowledge. In the former case they can serve as training aids for teaching the operation of complex systems, especially if the model can be used to demonstrate the outcome of experiments. In the latter case they generate experiments to be performed to gather the missing data.

Adaptive and Maladaptive Implications of Reinforcement Learning Processes: Fronto-Striatal Loops and Behavioural Correlates

That humans and animals learn from interaction with the environment is a foundational idea underlying nearly all theories of learning and intelligence. Learning that certain outcomes are associated with specific actions or stimuli (both internal and external), is at the very core of the capacity to adapt behaviour to environmental changes. In the present work, appetitive and aversive reinforcement learning paradigms have been used to investigate the fronto-striatal loops and behavioural correlates of adaptive and maladaptive reinforcement learning processes, aiming to a deeper understanding of how cortical and subcortical substrates interacts between them and with other brain systems to support learning. By combining a large variety of neuroscientific approaches, including behavioral and psychophysiological methods, EEG and neuroimaging techniques, these studies aim at clarifying and advancing the knowledge of the neural bases and computational mechanisms of reinforcement learning, both in normal and neurologically impaired population.

Challenges and Opportunities of Machine Learning for Clinical and Omics Data

Clinical and omics data are a promising field of application for machine learning techniques even though these methods are not yet systematically adopted in healthcare institutions. Despite artificial intelligence has proved successful in terms of prediction of pathologies or identification of their causes, the systematic adoption of these techniques still presents challenging issues due to the peculiarities of the analysed data. The aim of this thesis is to apply machine learning algorithms to both clinical and omics data sets in order to predict a patient's state of health and get better insights on the possible causes of the analysed diseases. In doing so, many of the arising issues when working with medical data will be discussed while possible solutions will be proposed to make machine learning provide feasible results and possibly become an effective and reliable support tool for healthcare systems.

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.

Integrating Machine Learning Paradigms for Predictive Maintenance in the Fourth Industrial Revolution era

In the last decade, manufacturing companies have been facing two significant challenges. First, digitalization imposes adopting Industry 4.0 technologies and allows creating smart, connected, self-aware, and self-predictive factories. Second, the attention on sustainability imposes to evaluate and reduce the impact of the implemented solutions from economic and social points of view. In manufacturing companies, the maintenance of physical assets assumes a critical role. Increasing the reliability and the availability of production systems leads to the minimization of systems’ downtimes; In addition, the proper system functioning avoids production wastes and potentially catastrophic accidents. Digitalization and new ICT technologies have assumed a relevant role in maintenance strategies. They allow assessing the health condition of machinery at any point in time. Moreover, they allow predicting the future behavior of machinery so that maintenance interventions can be planned, and the useful life of components can be exploited until the time instant before their fault. This dissertation provides insights on Predictive Maintenance goals and tools in Industry 4.0 and proposes a novel data acquisition, processing, sharing, and storage framework that addresses typical issues machine producers and users encounter. The research elaborates on two research questions that narrow down the potential approaches to data acquisition, processing, and analysis for fault diagnostics in evolving environments. The research activity is developed according to a research framework, where the research questions are addressed by research levers that are explored according to research topics. Each topic requires a specific set of methods and approaches; however, the overarching methodological approach presented in this dissertation includes three fundamental aspects: the maximization of the quality level of input data, the use of Machine Learning methods for data analysis, and the use of case studies deriving from both controlled environments (laboratory) and real-world instances.

A take on complexity: bio-molecules and human metabolism interaction modelling for health and nutrition with machine learning

The advent of omic data production has opened many new perspectives in the quest for modelling complexity in biophysical systems. With the capability of characterizing a complex organism through the patterns of its molecular states, observed at different levels through various omics, a new paradigm of investigation is arising. In this thesis, we investigate the links between perturbations of the human organism, described as the ensemble of crosstalk of its molecular states, and health. Machine learning plays a key role within this picture, both in omic data analysis and model building. We propose and discuss different frameworks developed by the author using machine learning for data reduction, integration, projection on latent features, pattern analysis, classification and clustering of omic data, with a focus on 1H NMR metabolomic spectral data. The aim is to link different levels of omic observations of molecular states, from nanoscale to macroscale, to study perturbations such as diseases and diet interpreted as changes in molecular patterns. The first part of this work focuses on the fingerprinting of diseases, linking cellular and systemic metabolomics with genomic to asses and predict the downstream of perturbations all the way down to the enzymatic network. The second part is a set of frameworks and models, developed with 1H NMR metabolomic at its core, to study the exposure of the human organism to diet and food intake in its full complexity, from epidemiological data analysis to molecular characterization of food structure.

Flexible Computing Systems For AI Acceleration At The Extreme Edge Of The IoT

Embedding intelligence in extreme edge devices allows distilling raw data acquired from sensors into actionable information, directly on IoT end-nodes. This computing paradigm, in which end-nodes no longer depend entirely on the Cloud, offers undeniable benefits, driving a large research area (TinyML) to deploy leading Machine Learning (ML) algorithms on micro-controller class of devices. To fit the limited memory storage capability of these tiny platforms, full-precision Deep Neural Networks (DNNs) are compressed by representing their data down to byte and sub-byte formats, in the integer domain. However, the current generation of micro-controller systems can barely cope with the computing requirements of QNNs. This thesis tackles the challenge from many perspectives, presenting solutions both at software and hardware levels, exploiting parallelism, heterogeneity and software programmability to guarantee high flexibility and high energy-performance proportionality. The first contribution, PULP-NN, is an optimized software computing library for QNN inference on parallel ultra-low-power (PULP) clusters of RISC-V processors, showing one order of magnitude improvements in performance and energy efficiency, compared to current State-of-the-Art (SoA) STM32 micro-controller systems (MCUs) based on ARM Cortex-M cores. The second contribution is XpulpNN, a set of RISC-V domain specific instruction set architecture (ISA) extensions to deal with sub-byte integer arithmetic computation. The solution, including the ISA extensions and the micro-architecture to support them, achieves energy efficiency comparable with dedicated DNN accelerators and surpasses the efficiency of SoA ARM Cortex-M based MCUs, such as the low-end STM32M4 and the high-end STM32H7 devices, by up to three orders of magnitude. To overcome the Von Neumann bottleneck while guaranteeing the highest flexibility, the final contribution integrates an Analog In-Memory Computing accelerator into the PULP cluster, creating a fully programmable heterogeneous fabric that demonstrates end-to-end inference capabilities of SoA MobileNetV2 models, showing two orders of magnitude performance improvements over current SoA analog/digital solutions.

Methods for integrating machine learning and constrained optimization

In the framework of industrial problems, the application of Constrained Optimization is known to have overall very good modeling capability and performance and stands as one of the most powerful, explored, and exploited tool to address prescriptive tasks. The number of applications is huge, ranging from logistics to transportation, packing, production, telecommunication, scheduling, and much more. The main reason behind this success is to be found in the remarkable effort put in the last decades by the OR community to develop realistic models and devise exact or approximate methods to solve the largest variety of constrained or combinatorial optimization problems, together with the spread of computational power and easily accessible OR software and resources. On the other hand, the technological advancements lead to a data wealth never seen before and increasingly push towards methods able to extract useful knowledge from them; among the data-driven methods, Machine Learning techniques appear to be one of the most promising, thanks to its successes in domains like Image Recognition, Natural Language Processes and playing games, but also the amount of research involved. The purpose of the present research is to study how Machine Learning and Constrained Optimization can be used together to achieve systems able to leverage the strengths of both methods: this would open the way to exploiting decades of research on resolution techniques for COPs and constructing models able to adapt and learn from available data. In the first part of this work, we survey the existing techniques and classify them according to the type, method, or scope of the integration; subsequently, we introduce a novel and general algorithm devised to inject knowledge into learning models through constraints, Moving Target. In the last part of the thesis, two applications stemming from real-world projects and done in collaboration with Optit will be presented.