Simulating event related potentials in tasks involving conflict resolution: a neural network

In this thesis, the main Executive Control theories are exposed. Methods typical of Cognitive and Computational Neuroscience are introduced and the role of behavioural tasks involving conflict resolution in the response elaboration, after the presentation of a stimulus to the subject, are highlighted. In particular, the Eriksen Flanker Task and its variants are discussed. Behavioural data, from scientific literature, are illustrated in terms of response times and error rates. During experimental behavioural tasks, EEG is registered simultaneously. Thanks to this, event related potential, related with the current task, can be studied. Different theories regarding relevant event related potential in this field - such as N2, fERN (feedback Error Related Negativity) and ERN (Error Related Negativity) – are introduced. The aim of this thesis is to understand and simulate processes regarding Executive Control, including performance improvement, error detection mechanisms, post error adjustments and the role of selective attention, with the help of an original neural network model. The network described here has been built with the purpose to simulate behavioural results of a four choice Eriksen Flanker Task. Model results show that the neural network can simulate response times, error rates and event related potentials quite well. Finally, results are compared with behavioural data and discussed in light of the mentioned Executive Control theories. Future perspective for this new model are outlined.

Structure learning of graphical models for task-oriented robot grasping

In the collective imaginaries a robot is a human like machine as any androids in science fiction. However the type of robots that you will encounter most frequently are machinery that do work that is too dangerous, boring or onerous. Most of the robots in the world are of this type. They can be found in auto, medical, manufacturing and space industries. Therefore a robot is a system that contains sensors, control systems, manipulators, power supplies and software all working together to perform a task. The development and use of such a system is an active area of research and one of the main problems is the development of interaction skills with the surrounding environment, which include the ability to grasp objects. To perform this task the robot needs to sense the environment and acquire the object informations, physical attributes that may influence a grasp. Humans can solve this grasping problem easily due to their past experiences, that is why many researchers are approaching it from a machine learning perspective finding grasp of an object using information of already known objects. But humans can select the best grasp amongst a vast repertoire not only considering the physical attributes of the object to grasp but even to obtain a certain effect. This is why in our case the study in the area of robot manipulation is focused on grasping and integrating symbolic tasks with data gained through sensors. The learning model is based on Bayesian Network to encode the statistical dependencies between the data collected by the sensors and the symbolic task. This data representation has several advantages. It allows to take into account the uncertainty of the real world, allowing to deal with sensor noise, encodes notion of causality and provides an unified network for learning. Since the network is actually implemented and based on the human expert knowledge, it is very interesting to implement an automated method to learn the structure as in the future more tasks and object features can be introduced and a complex network design based only on human expert knowledge can become unreliable. Since structure learning algorithms presents some weaknesses, the goal of this thesis is to analyze real data used in the network modeled by the human expert, implement a feasible structure learning approach and compare the results with the network designed by the expert in order to possibly enhance it.

Study of a wind-wave numerical model and its integration with ocean and oil-spill numerical models

The ability to represent the transport and fate of an oil slick at the sea surface is a formidable task. By using an accurate numerical representation of oil evolution and movement in seawater, the possibility to asses and reduce the oil-spill pollution risk can be greatly improved. The blowing of the wind on the sea surface generates ocean waves, which give rise to transport of pollutants by wave-induced velocities that are known as Stokes’ Drift velocities. The Stokes’ Drift transport associated to a random gravity wave field is a function of the wave Energy Spectra that statistically fully describe it and that can be provided by a wave numerical model. Therefore, in order to perform an accurate numerical simulation of the oil motion in seawater, a coupling of the oil-spill model with a wave forecasting model is needed. In this Thesis work, the coupling of the MEDSLIK-II oil-spill numerical model with the SWAN wind-wave numerical model has been performed and tested. In order to improve the knowledge of the wind-wave model and its numerical performances, a preliminary sensitivity study to different SWAN model configuration has been carried out. The SWAN model results have been compared with the ISPRA directional buoys located at Venezia, Ancona and Monopoli and the best model settings have been detected. Then, high resolution currents provided by a relocatable model (SURF) have been used to force both the wave and the oil-spill models and its coupling with the SWAN model has been tested. The trajectories of four drifters have been simulated by using JONSWAP parametric spectra or SWAN directional-frequency energy output spectra and results have been compared with the real paths traveled by the drifters.

OpenMP task scheduling strategies to mitigate hardware variability in tightly-coupled shared memory clusters

In questa tesi sono stati apportati due importanti contributi nel campo degli acceleratori embedded many-core. Abbiamo implementato un runtime OpenMP ottimizzato per la gestione del tasking model per sistemi a processori strettamente accoppiati in cluster e poi interconnessi attraverso una network on chip. Ci siamo focalizzati sulla loro scalabilità e sul supporto di task di granularità fine, come è tipico nelle applicazioni embedded. Il secondo contributo di questa tesi è stata proporre una estensione del runtime di OpenMP che cerca di prevedere la manifestazione di errori dati da fenomeni di variability tramite una schedulazione efficiente del carico di lavoro.

End-to-end Deep Metric Learning con Vision-Language Model per il Fashion Image Captioning

L'image captioning è un task di machine learning che consiste nella generazione di una didascalia, o caption, che descriva le caratteristiche di un'immagine data in input. Questo può essere applicato, ad esempio, per descrivere in dettaglio i prodotti in vendita su un sito di e-commerce, migliorando l'accessibilità del sito web e permettendo un acquisto più consapevole ai clienti con difficoltà visive. La generazione di descrizioni accurate per gli articoli di moda online è importante non solo per migliorare le esperienze di acquisto dei clienti, ma anche per aumentare le vendite online. Oltre alla necessità di presentare correttamente gli attributi degli articoli, infatti, descrivere i propri prodotti con il giusto linguaggio può contribuire a catturare l'attenzione dei clienti. In questa tesi, ci poniamo l'obiettivo di sviluppare un sistema in grado di generare una caption che descriva in modo dettagliato l'immagine di un prodotto dell'industria della moda dato in input, sia esso un capo di vestiario o un qualche tipo di accessorio. A questo proposito, negli ultimi anni molti studi hanno proposto soluzioni basate su reti convoluzionali e LSTM. In questo progetto proponiamo invece un'architettura encoder-decoder, che utilizza il modello Vision Transformer per la codifica delle immagini e GPT-2 per la generazione dei testi. Studiamo inoltre come tecniche di deep metric learning applicate in end-to-end durante l'addestramento influenzino le metriche e la qualità delle caption generate dal nostro modello.

Vocabulary Transfer and Knowledge Distillation for Language Model Compression

Natural Language Processing (NLP) has seen tremendous improvements over the last few years. Transformer architectures achieved impressive results in almost any NLP task, such as Text Classification, Machine Translation, and Language Generation. As time went by, transformers continued to improve thanks to larger corpora and bigger networks, reaching hundreds of billions of parameters. Training and deploying such large models has become prohibitively expensive, such that only big high tech companies can afford to train those models. Therefore, a lot of research has been dedicated to reducing a model’s size. In this thesis, we investigate the effects of Vocabulary Transfer and Knowledge Distillation for compressing large Language Models. The goal is to combine these two methodologies to further compress models without significant loss of performance. In particular, we designed different combination strategies and conducted a series of experiments on different vertical domains (medical, legal, news) and downstream tasks (Text Classification and Named Entity Recognition). Four different methods involving Vocabulary Transfer (VIPI) with and without a Masked Language Modelling (MLM) step and with and without Knowledge Distillation are compared against a baseline that assigns random vectors to new elements of the vocabulary. Results indicate that VIPI effectively transfers information of the original vocabulary and that MLM is beneficial. It is also noted that both vocabulary transfer and knowledge distillation are orthogonal to one another and may be applied jointly. The application of knowledge distillation first before subsequently applying vocabulary transfer is recommended. Finally, model performance due to vocabulary transfer does not always show a consistent trend as the vocabulary size is reduced. Hence, the choice of vocabulary size should be empirically selected by evaluation on the downstream task similar to hyperparameter tuning.

Intermediate linguistic task fine-tuning on Multi-lingual models

State-of-the-art NLP systems are generally based on the assumption that the underlying models are provided with vast datasets to train on. However, especially when working in multi-lingual contexts, datasets are often scarce, thus more research should be carried out in this field. This thesis investigates the benefits of introducing an additional training step when fine-tuning NLP models, named Intermediate Training, which could be exploited to augment the data used for the training phase. The Intermediate Training step is applied by training models on NLP tasks that are not strictly related to the target task, aiming to verify if the models are able to leverage the learned knowledge of such tasks. Furthermore, in order to better analyze the synergies between different categories of NLP tasks, experimentations have been extended also to Multi-Task Training, in which the model is trained on multiple tasks at the same time.

Meta-learning for informed model searches in Automated Machine Learning

Day by day, machine learning is changing our lives in ways we could not have imagined just 5 years ago. ML expertise is more and more requested and needed, though just a limited number of ML engineers are available on the job market, and their knowledge is always limited by an inherent characteristic of theirs: they are humans. This thesis explores the possibilities offered by meta-learning, a new field in ML that takes learning a level higher: models are trained on other models' training data, starting from features of the dataset they were trained on, inference times, obtained performances, to try to understand the relationship between a good model and the way it was obtained. The so-called metamodel was trained on data collected by OpenML, the largest ML metadata platform that's publicly available today. Datasets were analyzed to obtain meta-features that describe them, which were then tied to model performances in a regression task. The obtained metamodel predicts the expected performances of a given model type (e.g., a random forest) on a given ML task (e.g., classification on the UCI census dataset). This research was then integrated into a custom-made AutoML framework, to show how meta-learning is not an end in itself, but it can be used to further progress our ML research. Encoding ML engineering expertise in a model allows better, faster, and more impactful ML applications across the whole world, while reducing the cost that is inevitably tied to human engineers.

Machine Learning in Automatic Tabulation for Constraint Model Reformulation

Combinatorial decision and optimization problems belong to numerous applications, such as logistics and scheduling, and can be solved with various approaches. Boolean Satisfiability and Constraint Programming solvers are some of the most used ones and their performance is significantly influenced by the model chosen to represent a given problem. This has led to the study of model reformulation methods, one of which is tabulation, that consists in rewriting the expression of a constraint in terms of a table constraint. To apply it, one should identify which constraints can help and which can hinder the solving process. So far this has been performed by hand, for example in MiniZinc, or automatically with manually designed heuristics, in Savile Row. Though, it has been shown that the performances of these heuristics differ across problems and solvers, in some cases helping and in others hindering the solving procedure. However, recent works in the field of combinatorial optimization have shown that Machine Learning (ML) can be increasingly useful in the model reformulation steps. This thesis aims to design a ML approach to identify the instances for which Savile Row’s heuristics should be activated. Additionally, it is possible that the heuristics miss some good tabulation opportunities, so we perform an exploratory analysis for the creation of a ML classifier able to predict whether or not a constraint should be tabulated. The results reached towards the first goal show that a random forest classifier leads to an increase in the performances of 4 different solvers. The experimental results in the second task show that a ML approach could improve the performance of a solver for some problem classes.