Variational and learning models for image and time series inverse problems

Inverse problems are at the core of many challenging applications. Variational and learning models provide estimated solutions of inverse problems as the outcome of specific reconstruction maps. In the variational approach, the result of the reconstruction map is the solution of a regularized minimization problem encoding information on the acquisition process and prior knowledge on the solution. In the learning approach, the reconstruction map is a parametric function whose parameters are identified by solving a minimization problem depending on a large set of data. In this thesis, we go beyond this apparent dichotomy between variational and learning models and we show they can be harmoniously merged in unified hybrid frameworks preserving their main advantages. We develop several highly efficient methods based on both these model-driven and data-driven strategies, for which we provide a detailed convergence analysis. The arising algorithms are applied to solve inverse problems involving images and time series. For each task, we show the proposed schemes improve the performances of many other existing methods in terms of both computational burden and quality of the solution. In the first part, we focus on gradient-based regularized variational models which are shown to be effective for segmentation purposes and thermal and medical image enhancement. We consider gradient sparsity-promoting regularized models for which we develop different strategies to estimate the regularization strength. Furthermore, we introduce a novel gradient-based Plug-and-Play convergent scheme considering a deep learning based denoiser trained on the gradient domain. In the second part, we address the tasks of natural image deblurring, image and video super resolution microscopy and positioning time series prediction, through deep learning based methods. We boost the performances of supervised, such as trained convolutional and recurrent networks, and unsupervised deep learning strategies, such as Deep Image Prior, by penalizing the losses with handcrafted regularization terms.

Fractal descriptors for quantifying brain complexity in MRI

Magnetic Resonance Imaging (MRI) is the in vivo technique most commonly employed to characterize changes in brain structures. The conventional MRI-derived morphological indices are able to capture only partial aspects of brain structural complexity. Fractal geometry and its most popular index, the fractal dimension (FD), can characterize self-similar structures including grey matter (GM) and white matter (WM). Previous literature shows the need for a definition of the so-called fractal scaling window, within which each structure manifests self-similarity. This justifies the existence of fractal properties and confirms Mandelbrot’s assertion that "fractals are not a panacea; they are not everywhere". In this work, we propose a new approach to automatically determine the fractal scaling window, computing two new fractal descriptors, i.e., the minimal and maximal fractal scales (mfs and Mfs). Our method was implemented in a software package, validated on phantoms and applied on large datasets of structural MR images. We demonstrated that the FD is a useful marker of morphological complexity changes that occurred during brain development and aging and, using ultra-high magnetic field (7T) examinations, we showed that the cerebral GM has fractal properties also below the spatial scale of 1 mm. We applied our methodology in two neurological diseases. We observed the reduction of the brain structural complexity in SCA2 patients and, using a machine learning approach, proved that the cerebral WM FD is a consistent feature in predicting cognitive decline in patients with small vessel disease and mild cognitive impairment. Finally, we showed that the FD of the WM skeletons derived from diffusion MRI provides complementary information to those obtained from the FD of the WM general structure in T1-weighted images. In conclusion, the fractal descriptors of structural brain complexity are candidate biomarkers to detect subtle morphological changes during development, aging and in neurological diseases.

Portfolio optimization in the energy market

Let’s put ourselves in the shoes of an energy company. Our fleet of electricity production plants mainly includes gas, hydroelectric and waste-to-energy plants. We also sold contracts for the supply of gas and electricity. For each year we have to plan the trading of the volumes needed by the plants and customers: better to fix the price of these volumes in advance with the so-called forward contracts, instead of waiting for the delivery months, exposing ourselves to price uncertainty. Here’s the thing: trying to keep uncertainty under control in a market that has never shown such extreme scenarios as in recent years: a pandemic, a worsening climate crisis and a war that is affecting economies around the world have made the energy market more volatile than ever. How to make decisions in such uncertain contexts? There is an optimization problem: given a year, we need to choose the optimal planning of volume trading times, to meet the needs of our portfolio at the best prices, taking into account the liquidity constraints given by the market and the risk constraints imposed by the company. Algorithms are needed for the generation of market scenarios over a finite time horizon, that is, a probabilistic distribution that allows a view of all the dates between now and the end of the year of interest. Algorithms are needed to solve the optimization problem: we have proposed more than one and compared them; a very simple one, which avoids considering part of the complexity, moving on to a scenario approach and finally a reinforcement learning approach.

Supervised and weakly supervised counting-by-segmentation: the fluorescent microscopy use case

This thesis focuses on automating the time-consuming task of manually counting activated neurons in fluorescent microscopy images, which is used to study the mechanisms underlying torpor. The traditional method of manual annotation can introduce bias and delay the outcome of experiments, so the author investigates a deep-learning-based procedure to automatize this task. The author explores two of the main convolutional-neural-network (CNNs) state-of-the-art architectures: UNet and ResUnet family model, and uses a counting-by-segmentation strategy to provide a justification of the objects considered during the counting process. The author also explores a weakly-supervised learning strategy that exploits only dot annotations. The author quantifies the advantages in terms of data reduction and counting performance boost obtainable with a transfer-learning approach and, specifically, a fine-tuning procedure. The author released the dataset used for the supervised use case and all the pre-training models, and designed a web application to share both the counting process pipeline developed in this work and the models pre-trained on the dataset analyzed in this work.

Promuovere l'autovalutazione e il miglioramento delle strategie di apprendimento degli studenti internazionali cinesi: una ricerca empirica presso l'Università di Bologna

Nel quadro di alcuni filoni di ricerca inerenti alla promozione delle strategie cognitive, metacognitive e motivazionali degli studenti per una migliore efficacia del loro apprendimento (anche a livello universitario), il contributo presenta l’impianto e gli esiti di una ricerca empirica volta a indagare le percezioni degli studenti internazionali cinesi sulla loro esperienza universitaria in Italia, con un focus sulle eventuali difficoltà nell’adozione di un approccio autonomo e strategico all’apprendimento, e a sperimentare un intervento formativo messo a punto per sostenerli nel miglioramento del loro approccio all’apprendimento attraverso l’uso di procedure sistematiche di autoriflessione, self-recording e autovalutazione supportate dalla ricercatrice. Il disegno della ricerca è un quasi-esperimento a due gruppi con pre-test e post-test. Il campione è costituito da 60 studenti di diversi Dipartimenti dell’Università di Bologna che hanno partecipato volontariamente alla ricerca, di cui 30 hanno preso parte all’intervento. Gli strumenti utilizzati per la misurazione in ingresso e in uscita sono il Questionario sui Processi di Apprendimento e alcune scale del Questionario sulle Strategie di Apprendimento. Agli studenti del gruppo sperimentale è stato somministrato anche un questionario finale di valutazione del percorso formativo. Sono state inoltre effettuate alcune interviste a distanza di tempo come fase di follow up. Gli studenti in entrambi i gruppi affrontano sfide relative all’ambientamento nel contesto universitario italiano, con particolare riferimento a difficoltà linguistiche e di integrazione sociale. I principali fattori influenti sull’efficacia dello studio includono le barriere linguistiche, la gestione del tempo, la consapevolezza e l’uso delle strategie di studio. Nonostante emerga un miglioramento del gruppo sperimentale tra pre e post test, le differenze tra i due gruppi non sono risultate statisticamente significative. Tuttavia, i feedback forniti dagli studenti nel questionario di soddisfazione per il percorso formativo e nelle interviste post-intervento evidenziano percezioni positive sull’utilità del percorso, con benefici relativi al loro approccio allo studio.

Applied deep learning and data science with a human-centric and data-centric approach

The term Artificial intelligence acquired a lot of baggage since its introduction and in its current incarnation is synonymous with Deep Learning. The sudden availability of data and computing resources has opened the gates to myriads of applications. Not all are created equal though, and problems might arise especially for fields not closely related to the tasks that pertain tech companies that spearheaded DL. The perspective of practitioners seems to be changing, however. Human-Centric AI emerged in the last few years as a new way of thinking DL and AI applications from the ground up, with a special attention at their relationship with humans. The goal is designing a system that can gracefully integrate in already established workflows, as in many real-world scenarios AI may not be good enough to completely replace its humans. Often this replacement may even be unneeded or undesirable. Another important perspective comes from, Andrew Ng, a DL pioneer, who recently started shifting the focus of development from “better models” towards better, and smaller, data. He defined his approach Data-Centric AI. Without downplaying the importance of pushing the state of the art in DL, we must recognize that if the goal is creating a tool for humans to use, more raw performance may not align with more utility for the final user. A Human-Centric approach is compatible with a Data-Centric one, and we find that the two overlap nicely when human expertise is used as the driving force behind data quality. This thesis documents a series of case-studies where these approaches were employed, to different extents, to guide the design and implementation of intelligent systems. We found human expertise proved crucial in improving datasets and models. The last chapter includes a slight deviation, with studies on the pandemic, still preserving the human and data centric perspective.

Investigating the learning potential of the Second Quantum Revolution: development of an approach for secondary school students

In recent years we have witnessed important changes: the Second Quantum Revolution is in the spotlight of many countries, and it is creating a new generation of technologies. To unlock the potential of the Second Quantum Revolution, several countries have launched strategic plans and research programs that finance and set the pace of research and development of these new technologies (like the Quantum Flagship, the National Quantum Initiative Act and so on). The increasing pace of technological changes is also challenging science education and institutional systems, requiring them to help to prepare new generations of experts. This work is placed within physics education research and contributes to the challenge by developing an approach and a course about the Second Quantum Revolution. The aims are to promote quantum literacy and, in particular, to value from a cultural and educational perspective the Second Revolution. The dissertation is articulated in two parts. In the first, we unpack the Second Quantum Revolution from a cultural perspective and shed light on the main revolutionary aspects that are elevated to the rank of principles implemented in the design of a course for secondary school students, prospective and in-service teachers. The design process and the educational reconstruction of the activities are presented as well as the results of a pilot study conducted to investigate the impact of the approach on students' understanding and to gather feedback to refine and improve the instructional materials. The second part consists of the exploration of the Second Quantum Revolution as a context to introduce some basic concepts of quantum physics. We present the results of an implementation with secondary school students to investigate if and to what extent external representations could play any role to promote students’ understanding and acceptance of quantum physics as a personal reliable description of the world.

Computational creativity: an interdisciplinary approach to sequential learning and creative generations

Creativity seems mysterious; when we experience a creative spark, it is difficult to explain how we got that idea, and we often recall notions like ``inspiration" and ``intuition" when we try to explain the phenomenon. The fact that we are clueless about how a creative idea manifests itself does not necessarily imply that a scientific explanation cannot exist. We are unaware of how we perform certain tasks, such as biking or language understanding, but we have more and more computational techniques that can replicate and hopefully explain such activities. We should understand that every creative act is a fruit of experience, society, and culture. Nothing comes from nothing. Novel ideas are never utterly new; they stem from representations that are already in mind. Creativity involves establishing new relations between pieces of information we had already: then, the greater the knowledge, the greater the possibility of finding uncommon connections, and the more the potential to be creative. In this vein, a beneficial approach to a better understanding of creativity must include computational or mechanistic accounts of such inner procedures and the formation of the knowledge that enables such connections. That is the aim of Computational Creativity: to develop computational systems for emulating and studying creativity. Hence, this dissertation focuses on these two related research areas: discussing computational mechanisms to generate creative artifacts and describing some implicit cognitive processes that can form the basis for creative thoughts.

Machine-learning methods for structure prediction of β-barrel membrane proteins

Different types of proteins exist with diverse functions that are essential for living organisms. An important class of proteins is represented by transmembrane proteins which are specifically designed to be inserted into biological membranes and devised to perform very important functions in the cell such as cell communication and active transport across the membrane. Transmembrane β-barrels (TMBBs) are a sub-class of membrane proteins largely under-represented in structure databases because of the extreme difficulty in experimental structure determination. For this reason, computational tools that are able to predict the structure of TMBBs are needed. In this thesis, two computational problems related to TMBBs were addressed: the detection of TMBBs in large datasets of proteins and the prediction of the topology of TMBB proteins. Firstly, a method for TMBB detection was presented based on a novel neural network framework for variable-length sequence classification. The proposed approach was validated on a non-redundant dataset of proteins. Furthermore, we carried-out genome-wide detection using the entire Escherichia coli proteome. In both experiments, the method significantly outperformed other existing state-of-the-art approaches, reaching very high PPV (92%) and MCC (0.82). Secondly, a method was also introduced for TMBB topology prediction. The proposed approach is based on grammatical modelling and probabilistic discriminative models for sequence data labeling. The method was evaluated using a newly generated dataset of 38 TMBB proteins obtained from high-resolution data in the PDB. Results have shown that the model is able to correctly predict topologies of 25 out of 38 protein chains in the dataset. When tested on previously released datasets, the performances of the proposed approach were measured as comparable or superior to the current state-of-the-art of TMBB topology prediction.