Deep learning for computer vision: a comparison between convolutional neural networks and hierarchical temporal memories on object recognition tasks

In recent years, Deep Learning techniques have shown to perform well on a large variety of problems both in Computer Vision and Natural Language Processing, reaching and often surpassing the state of the art on many tasks. The rise of deep learning is also revolutionizing the entire field of Machine Learning and Pattern Recognition pushing forward the concepts of automatic feature extraction and unsupervised learning in general. However, despite the strong success both in science and business, deep learning has its own limitations. It is often questioned if such techniques are only some kind of brute-force statistical approaches and if they can only work in the context of High Performance Computing with tons of data. Another important question is whether they are really biologically inspired, as claimed in certain cases, and if they can scale well in terms of "intelligence". The dissertation is focused on trying to answer these key questions in the context of Computer Vision and, in particular, Object Recognition, a task that has been heavily revolutionized by recent advances in the field. Practically speaking, these answers are based on an exhaustive comparison between two, very different, deep learning techniques on the aforementioned task: Convolutional Neural Network (CNN) and Hierarchical Temporal memory (HTM). They stand for two different approaches and points of view within the big hat of deep learning and are the best choices to understand and point out strengths and weaknesses of each of them. CNN is considered one of the most classic and powerful supervised methods used today in machine learning and pattern recognition, especially in object recognition. CNNs are well received and accepted by the scientific community and are already deployed in large corporation like Google and Facebook for solving face recognition and image auto-tagging problems. HTM, on the other hand, is known as a new emerging paradigm and a new meanly-unsupervised method, that is more biologically inspired. It tries to gain more insights from the computational neuroscience community in order to incorporate concepts like time, context and attention during the learning process which are typical of the human brain. In the end, the thesis is supposed to prove that in certain cases, with a lower quantity of data, HTM can outperform CNN.

An X-ray study of CIV-selected AGN in the COSMOS field

Negli ultimi vent’anni innumerevoli sforzi sono stati compiuti a livello internazionale per ottenere un censimento completo degli “Active Galactic Nuclei” (AGN), ovvero di nuclei galattici attivi, oscurati in banda X. Tale censimento potrebbe rappresentare infatti la soluzione alla problematica del cosiddetto fondo cosmico non risolto in banda X. Gli studi finora condotti sfruttano la forte correlazione fra l'attività del SMBH e l'evoluzione della galassia ospite attraverso osservazioni in banda X hard, nel vicino-medio infrarosso e nell'ottico. Questa tesi si colloca in questo scenario con lo scopo di verificare e confermare l'affidabilità della selezione tramite la riga di emissione del CIV a 1549 Å di AGN oscurati fino a z≈3. Per raggiungere tale obiettivo è stato assunto che il CIV rappresenti un indicatore affidabile della luminosità intrinseca degli AGN e del loro alto potenziale di ionizzazione. Inoltre, allo studio in banda ottica delle sorgenti sono stati associati i dati profondi in banda X per analizzarne le proprietà X e caratterizzarne l’ammontare dell’oscuramento in tale banda in termini di densità di colonna di idrogeno. In particolare, in questo lavoro vengono presentati i risultati dell’analisi in banda X del campione di 192 AGN selezionati nella survey ottica zCOSMOS-Deep, attraverso la riga di emissione del CIV a 1549 Å. Queste 192 sorgenti hanno un redshift medio di 2.2 e una magnitudine media AB in banda B di 23.7. La copertura in banda X del campo selezionato è data dalla survey Chandra COSMOS-Legacy comprendente 4.6 Ms di osservazioni in un’area di 2.2 deg2. I risultati ottenuti in questo progetto di tesi tramite la selezione possono ritenersi soddisfacenti: metà delle AGN di Tipo 2 selezionate con il CIV e rilevate in banda X risultano fortemente oscurate (NH>10^23 cm^(-2) ). Inoltre, le AGN di Tipo 2 non rilevate in banda X risultano consistenti con uno scenario di oggetti oscurati.

Deep Learning Architectures for time of arrival detection in Acoustic Emissions Monitoring

Acoustic Emission (AE) monitoring can be used to detect the presence of damage as well as determine its location in Structural Health Monitoring (SHM) applications. Information on the time difference of the signal generated by the damage event arriving at different sensors is essential in performing localization. This makes the time of arrival (ToA) an important piece of information to retrieve from the AE signal. Generally, this is determined using statistical methods such as the Akaike Information Criterion (AIC) which is particularly prone to errors in the presence of noise. And given that the structures of interest are surrounded with harsh environments, a way to accurately estimate the arrival time in such noisy scenarios is of particular interest. In this work, two new methods are presented to estimate the arrival times of AE signals which are based on Machine Learning. Inspired by great results in the field, two models are presented which are Deep Learning models - a subset of machine learning. They are based on Convolutional Neural Network (CNN) and Capsule Neural Network (CapsNet). The primary advantage of such models is that they do not require the user to pre-define selected features but only require raw data to be given and the models establish non-linear relationships between the inputs and outputs. The performance of the models is evaluated using AE signals generated by a custom ray-tracing algorithm by propagating them on an aluminium plate and compared to AIC. It was found that the relative error in estimation on the test set was < 5% for the models compared to around 45% of AIC. The testing process was further continued by preparing an experimental setup and acquiring real AE signals to test on. Similar performances were observed where the two models not only outperform AIC by more than a magnitude in their average errors but also they were shown to be a lot more robust as compared to AIC which fails in the presence of noise.

Deep learning models for the automatic analysis of volleyball plays

Collecting and analysing data is an important element in any field of human activity and research. Even in sports, collecting and analyzing statistical data is attracting a growing interest. Some exemplar use cases are: improvement of technical/tactical aspects for team coaches, definition of game strategies based on the opposite team play or evaluation of the performance of players. Other advantages are related to taking more precise and impartial judgment in referee decisions: a wrong decision can change the outcomes of important matches. Finally, it can be useful to provide better representations and graphic effects that make the game more engaging for the audience during the match. Nowadays it is possible to delegate this type of task to automatic software systems that can use cameras or even hardware sensors to collect images or data and process them. One of the most efficient methods to collect data is to process the video images of the sporting event through mixed techniques concerning machine learning applied to computer vision. As in other domains in which computer vision can be applied, the main tasks in sports are related to object detection, player tracking, and to the pose estimation of athletes. The goal of the present thesis is to apply different models of CNNs to analyze volleyball matches. Starting from video frames of a volleyball match, we reproduce a bird's eye view of the playing court where all the players are projected, reporting also for each player the type of action she/he is performing.