Machine learning "as a service" for high energy physics (MLaaS4HEP): evolution of a framework for ML-based physics analyses

The scientific success of the LHC experiments at CERN highly depends on the availability of computing resources which efficiently store, process, and analyse the amount of data collected every year. This is ensured by the Worldwide LHC Computing Grid infrastructure that connect computing centres distributed all over the world with high performance network. LHC has an ambitious experimental program for the coming years, which includes large investments and improvements both for the hardware of the detectors and for the software and computing systems, in order to deal with the huge increase in the event rate expected from the High Luminosity LHC (HL-LHC) phase and consequently with the huge amount of data that will be produced. Since few years the role of Artificial Intelligence has become relevant in the High Energy Physics (HEP) world. Machine Learning (ML) and Deep Learning algorithms have been successfully used in many areas of HEP, like online and offline reconstruction programs, detector simulation, object reconstruction, identification, Monte Carlo generation, and surely they will be crucial in the HL-LHC phase. This thesis aims at contributing to a CMS R&D project, regarding a ML "as a Service" solution for HEP needs (MLaaS4HEP). It consists in a data-service able to perform an entire ML pipeline (in terms of reading data, processing data, training ML models, serving predictions) in a completely model-agnostic fashion, directly using ROOT files of arbitrary size from local or distributed data sources. This framework has been updated adding new features in the data preprocessing phase, allowing more flexibility to the user. Since the MLaaS4HEP framework is experiment agnostic, the ATLAS Higgs Boson ML challenge has been chosen as physics use case, with the aim to test MLaaS4HEP and the contribution done with this work.

A Reinforcement Learning Agent for Distributed Task Allocation

Al giorno d'oggi il reinforcement learning ha dimostrato di essere davvero molto efficace nel machine learning in svariati campi, come ad esempio i giochi, il riconoscimento vocale e molti altri. Perciò, abbiamo deciso di applicare il reinforcement learning ai problemi di allocazione, in quanto sono un campo di ricerca non ancora studiato con questa tecnica e perchè questi problemi racchiudono nella loro formulazione un vasto insieme di sotto-problemi con simili caratteristiche, per cui una soluzione per uno di essi si estende ad ognuno di questi sotto-problemi. In questo progetto abbiamo realizzato un applicativo chiamato Service Broker, il quale, attraverso il reinforcement learning, apprende come distribuire l'esecuzione di tasks su dei lavoratori asincroni e distribuiti. L'analogia è quella di un cloud data center, il quale possiede delle risorse interne - possibilmente distribuite nella server farm -, riceve dei tasks dai suoi clienti e li esegue su queste risorse. L'obiettivo dell'applicativo, e quindi del data center, è quello di allocare questi tasks in maniera da minimizzare il costo di esecuzione. Inoltre, al fine di testare gli agenti del reinforcement learning sviluppati è stato creato un environment, un simulatore, che permettesse di concentrarsi nello sviluppo dei componenti necessari agli agenti, invece che doversi anche occupare di eventuali aspetti implementativi necessari in un vero data center, come ad esempio la comunicazione con i vari nodi e i tempi di latenza di quest'ultima. I risultati ottenuti hanno dunque confermato la teoria studiata, riuscendo a ottenere prestazioni migliori di alcuni dei metodi classici per il task allocation.

Detecting social patterns within 20th century documentary photos: a deep learning based approach

The job of a historian is to understand what happened in the past, resorting in many cases to written documents as a firsthand source of information. Text, however, does not amount to the only source of knowledge. Pictorial representations, in fact, have also accompanied the main events of the historical timeline. In particular, the opportunity of visually representing circumstances has bloomed since the invention of photography, with the possibility of capturing in real-time the occurrence of a specific events. Thanks to the widespread use of digital technologies (e.g. smartphones and digital cameras), networking capabilities and consequent availability of multimedia content, the academic and industrial research communities have developed artificial intelligence (AI) paradigms with the aim of inferring, transferring and creating new layers of information from images, videos, etc. Now, while AI communities are devoting much of their attention to analyze digital images, from an historical research standpoint more interesting results may be obtained analyzing analog images representing the pre-digital era. Within the aforementioned scenario, the aim of this work is to analyze a collection of analog documentary photographs, building upon state-of-the-art deep learning techniques. In particular, the analysis carried out in this thesis aims at producing two following results: (a) produce the date of an image, and, (b) recognizing its background socio-cultural context,as defined by a group of historical-sociological researchers. Given these premises, the contribution of this work amounts to: (i) the introduction of an historical dataset including images of “Family Album” among all the twentieth century, (ii) the introduction of a new classification task regarding the identification of the socio-cultural context of an image, (iii) the exploitation of different deep learning architectures to perform the image dating and the image socio-cultural context classification.

Smart sampling approaches for Decision-Focused Learning

Many real-word decision- making problems are defined based on forecast parameters: for example, one may plan an urban route by relying on traffic predictions. In these cases, the conventional approach consists in training a predictor and then solving an optimization problem. This may be problematic since mistakes made by the predictor may trick the optimizer into taking dramatically wrong decisions. Recently, the field of Decision-Focused Learning overcomes this limitation by merging the two stages at training time, so that predictions are rewarded and penalized based on their outcome in the optimization problem. There are however still significant challenges toward a widespread adoption of the method, mostly related to the limitation in terms of generality and scalability. One possible solution for dealing with the second problem is introducing a caching-based approach, to speed up the training process. This project aims to investigate these techniques, in order to reduce even more, the solver calls. For each considered method, we designed a particular smart sampling approach, based on their characteristics. In the case of the SPO method, we ended up discovering that it is only necessary to initialize the cache with only several solutions; those needed to filter the elements that we still need to properly learn. For the Blackbox method, we designed a smart sampling approach, based on inferred solutions.

Apprendimento di alberi di decisione

In questa tesi viene effettuata una panoramica sull'apprendimento di alberi di decisione (un particolare metodo di apprendimento supervisionato) e sulle varie tecniche per poterne migliorare le prestazioni. Vengono poi descritti alcuni algoritmi e ne vengono confrontate le prestazioni.

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.

An Embedded In-Cabin Lightweight High-Performance 3D Gaze Estimation System

Gaze estimation has gained interest in recent years for being an important cue to obtain information about the internal cognitive state of humans. Regardless of whether it is the 3D gaze vector or the point of gaze (PoG), gaze estimation has been applied in various fields, such as: human robot interaction, augmented reality, medicine, aviation and automotive. In the latter field, as part of Advanced Driver-Assistance Systems (ADAS), it allows the development of cutting-edge systems capable of mitigating road accidents by monitoring driver distraction. Gaze estimation can be also used to enhance the driving experience, for instance, autonomous driving. It also can improve comfort with augmented reality components capable of being commanded by the driver's eyes. Although, several high-performance real-time inference works already exist, just a few are capable of working with only a RGB camera on computationally constrained devices, such as a microcontroller. This work aims to develop a low-cost, efficient and high-performance embedded system capable of estimating the driver's gaze using deep learning and a RGB camera. The proposed system has achieved near-SOTA performances with about 90% less memory footprint. The capabilities to generalize in unseen environments have been evaluated through a live demonstration, where high performance and near real-time inference were obtained using a webcam and a Raspberry Pi4.

Convolutional Neural Network Architectures for Template Matching

The Neural Networks customized and tested in this thesis (WaldoNet, FlowNet and PatchNet) are a first exploration and approach to the Template Matching task. The possibilities of extension are therefore many and some are proposed below. During my thesis, I have analyzed the functioning of the classical algorithms and adapted with deep learning algorithms. The features extracted from both the template and the query images resemble the keypoints of the SIFT algorithm. Then, instead of similarity function or keypoints matching, WaldoNet and PatchNet use the convolutional layer to compare the features, while FlowNet uses the correlational layer. In addition, I have identified the major challenges of the Template Matching task (affine/non-affine transformations, intensity changes...) and solved them with a careful design of the dataset.

Autonomous pagination for newspaper from a predefined plan

Description of the development of a product able to deliver an autonomous page construction from a predefined plan. The processes involve Machine Learning techniques for text fitting on shapes, Beam Search for associations and Deep Learning for autonomous cropping of images.

Predizione dell'effetto delle mutazioni sulla variazione della stabilita' proteica con metodi di "machine-learning".

La tesi consiste nell’implementare un software in grado a predire la variazione della stabilità di una proteina sottoposta ad una mutazione. Il predittore implementato fa utilizzo di tecniche di Machine-Learning ed, in particolare, di SVM. In particolare, riguarda l’analisi delle prestazioni di un predittore, precedentemente implementato, sotto opportune variazioni dei parametri di input e relativamente all’utilizzo di nuova informazione rispetto a quella utilizzata dal predittore basilare.

Le tecniche di machine learning per il trattamento della sindrome dell'arto fantasma

Questo elaborato ha come scopo quello di analizzare ed esaminare una patologia oggetto di attiva ricerca scientifica, la sindrome dell’arto fantasma o phantom limb pain: tracciando la storia delle terapie più utilizzate per la sua attenuazione, si è giunti ad analizzarne lo stato dell’arte. Consapevoli che la sindrome dell’arto fantasma costituisce, oltre che un disturbo per chi la prova, uno strumento assai utile per l’analisi delle attività nervose del segmento corporeo superstite (moncone), si è svolta un’attività al centro Inail di Vigorso di Budrio finalizzata a rilevare segnali elettrici provenienti dai monconi superiori dei pazienti che hanno subito un’amputazione. Avendo preliminarmente trattato l’argomento “Machine learning” per raggiungere una maggiore consapevolezza delle potenzialità dell’apprendimento automatico, si sono analizzate la attività neuronali dei pazienti mentre questi muovevano il loro arto fantasma per riuscire a settare nuove tipologie di protesi mobili in base ai segnali ricevuti dal moncone.

Machine Learning applicato al Web Semantico: Statistical Relational Learning vs Tensor Factorization

Obiettivo della tesi è analizzare e testare i principali approcci di Machine Learning applicabili in contesti semantici, partendo da algoritmi di Statistical Relational Learning, quali Relational Probability Trees, Relational Bayesian Classifiers e Relational Dependency Networks, per poi passare ad approcci basati su fattorizzazione tensori, in particolare CANDECOMP/PARAFAC, Tucker e RESCAL.

Predicting CMS datasets popularity with machine learning

In CMS è stato lanciato un progetto di Data Analytics e, all’interno di esso, un’attività specifica pilota che mira a sfruttare tecniche di Machine Learning per predire la popolarità dei dataset di CMS. Si tratta di un’osservabile molto delicata, la cui eventuale predizione premetterebbe a CMS di costruire modelli di data placement più intelligenti, ampie ottimizzazioni nell’uso dello storage a tutti i livelli Tiers, e formerebbe la base per l’introduzione di un solito sistema di data management dinamico e adattivo. Questa tesi descrive il lavoro fatto sfruttando un nuovo prototipo pilota chiamato DCAFPilot, interamente scritto in python, per affrontare questa sfida.

Big data, nosql e machine learning: un'applicazione di prediction e recommendation basata sulle api di Amazon

In questa tesi sono stati introdotti e studiati i Big Data, dando particolare importanza al mondo NoSQL, approfondendo MongoDB, e al mondo del Machine Learning, approfondendo PredictionIO. Successivamente è stata sviluppata un'applicazione attraverso l'utilizzo di tecnologie web, nodejs, node-webkit e le tecnologie approfondite prima. L'applicazione utilizza l'interpolazione polinomiale per predirre il prezzo di un bene salvato nello storico presente su MongoDB. Attraverso PredictionIO, essa analizza il comportamento degli altri utenti consigliando dei prodotti per l'acquisto. Infine è stata effetuata un'analisi dei risultati dell'errore prodotto dall'interpolazione.