Matteo Tiezzi

Matteo Tiezzi
Università degli Studi di Siena | UNISI · Department of Information Engineering and Mathematical

Doctor of Engineering
PostDoctoral Researcher

About

46
Publications
4,420
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
113
Citations
Introduction
I am a post-doctoral researcher in the Siena Artificial Intelligence Laboratory SAILab, tutored by Prof. Stefano Melacci. I obtained my PhD at the University of Siena, Italy, defending a thesis entitled “Local Propagation in Neural Network Learning by Architectural Constraints”. I am generally interested in Artificial Intelligence and other connected areas of computer science. My recent contributes are related to both the application of Deep Learning models to computer vision and video analysis
Additional affiliations
May 2017 - October 2017
IsTech
Position
  • Master's Student
Description
  • Master Scholarship: Traffic events monitoring with recurrent neural networks
April 2014 - August 2020
QuestIt
Position
  • Bachelor Scholarship
Description
  • Engineering Scholarship: Relavant Information extraction from web pages using XPath
Education
October 2014 - November 2017
Università degli Studi di Siena
Field of study
  • Information Engineering
October 2010 - November 2014
Università degli Studi di Siena
Field of study
  • Information Engineering

Publications

Publications (46)
Chapter
Efficiently learning unsupervised pixel-wise visual representations is crucial for training agents that can perceive their environment without relying on heavy human supervision or abundant annotated data. Motivated by recent work that promotes motion as a key source of information in representation learning, we propose a novel instance of contrast...
Preprint
Full-text available
This paper proposes Hamiltonian Learning, a novel unified framework for learning with neural networks "over time", i.e., from a possibly infinite stream of data, in an online manner, without having access to future information. Existing works focus on the simplified setting in which the stream has a known finite length or is segmented into smaller...
Preprint
Full-text available
Learning with neural networks from a continuous stream of visual information presents several challenges due to the non-i.i.d. nature of the data. However, it also offers novel opportunities to develop representations that are consistent with the information flow. In this paper we investigate the case of unsupervised continual learning of pixel-wis...
Preprint
Full-text available
Explainability in artificial intelligence (XAI) remains a crucial aspect for fostering trust and understanding in machine learning models. Current visual explanation techniques, such as gradient-based or class-activation-based methods, often exhibit a strong dependence on specific model architectures. Conversely, perturbation-based methods, despite...
Preprint
Full-text available
Effectively learning from sequential data is a longstanding goal of Artificial Intelligence, especially in the case of long sequences. From the dawn of Machine Learning, several researchers engaged in the search of algorithms and architectures capable of processing sequences of patterns, retaining information about the past inputs while still lever...
Article
Optimal control deals with optimization problems in which variables steer a dynamical system, and its outcome contributes to the objective function. Two classical approaches to solving these problems are Dynamic Programming and the Pontryagin Maximum Principle. In both approaches, Hamiltonian equations offer an interpretation of optimality through...
Preprint
Full-text available
The intrinsic difficulty in adapting deep learning models to non-stationary environments limits the applicability of neural networks to real-world tasks. This issue is critical in practical supervised learning settings, such as the ones in which a pre-trained model computes projections toward a latent space where different task predictors are seque...
Chapter
The classic computational scheme of convolutional layers leverages filter banks that are shared over all the spatial coordinates of the input, independently on external information on what is specifically under observation and without any distinctions between what is closer to the observed area and what is peripheral. In this paper we propose to go...
Chapter
The generation of aesthetically pleasing graph layouts is the main purpose of Graph Drawing techniques. Recent contributions delved into the usage of Gradient-descent (GD) based schemes to optimize differentiable loss functions, built to measure the graph layout adherence to given layout characteristics. However, some properties cannot be easily ex...
Preprint
Full-text available
In this paper, we present PARTIME, a software library written in Python and based on PyTorch, designed specifically to speed up neural networks whenever data is continuously streamed over time, for both learning and inference. Existing libraries are designed to exploit data-level parallelism, assuming that samples are batched, a condition that is n...
Chapter
Full-text available
Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in creating conditions for designing continuously evolving dynamics that are typical of the real-world. Many existing...
Conference Paper
Full-text available
Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented from leveraging large fully-annotated dataset, but rather the interactions with supervisory signals are sparsely...
Article
Full-text available
Graph drawing techniques have been developed in the last few years with the purpose of producing esthetically pleasing node-link layouts. Recently, the employment of differentiable loss functions has paved the road to the massive usage of gradient descent and related optimization algorithms. In this article, we propose a novel framework for the dev...
Article
Full-text available
Amongst a variety of approaches aimed at making the learning procedure of neural networks more effective, the scientific community developed strategies to order the examples according to their estimated complexity, to distil knowledge from larger networks, or to exploit the principles behind adversarial machine learning. A different idea has been r...
Preprint
Devising intelligent agents able to live in an environment and learn by observing the surroundings is a longstanding goal of Artificial Intelligence. From a bare Machine Learning perspective, challenges arise when the agent is prevented from leveraging large fully-annotated dataset, but rather the interactions with supervisory signals are sparsely...
Preprint
Full-text available
Amongst a variety of approaches aimed at making the learning procedure of neural networks more effective, the scientific community developed strategies to order the examples according to their estimated complexity, to distil knowledge from larger networks, or to exploit the principles behind adversarial machine learning. A different idea has been r...
Preprint
Full-text available
Graph Drawing techniques have been developed in the last few years with the purpose of producing aesthetically pleasing node-link layouts. Recently, the employment of differentiable loss functions has paved the road to the massive usage of Gradient Descent and related optimization algorithms. In this paper, we propose a novel framework for the deve...
Preprint
Full-text available
In the last few years, the scientific community showed a remarkable and increasing interest towards 3D Virtual Environments, training and testing Machine Learning-based models in realistic virtual worlds. On one hand, these environments could also become a mean to study the weaknesses of Machine Learning algorithms, or to simulate training settings...
Preprint
Full-text available
Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in creating conditions for designing continuously evolving dynamics that are typical of the real-world. Many existing...
Preprint
Full-text available
In the last decade, motivated by the success of Deep Learning, the scientific community proposed several approaches to make the learning procedure of Neural Networks more effective. When focussing on the way in which the training data are provided to the learning machine, we can distinguish between the classic random selection of stochastic gradien...
Article
Full-text available
The popularity of deep learning techniques renewed the interest in neural architectures able to process complex structures that can be represented using graphs, inspired by Graph Neural Networks (GNNs). We focus our attention on the originally proposed GNN model of Scarselli et al. 2009, which encodes the state of the nodes of the graph by means of...
Conference Paper
Full-text available
Italian is a Romance language that has its roots in Vulgar Latin. The birth of the modern Italian started in Tuscany around the 14th century, and it is mainly attributed to the works of Dante Alighieri, Francesco Petrarca and Giovanni Boccaccio, who are among the most acclaimed authors of the medieval age in Tuscany. However, Italy has been charact...
Conference Paper
Full-text available
Unsupervised learning from continuous visual streams is a challenging problem that cannot be naturally and efficiently managed in the classic batch-mode setting of computation. The information stream must be carefully processed accordingly to an appropriate spatio-temporal distribution of the visual data, while most approaches of learning commonly...
Preprint
Full-text available
Italian is a Romance language that has its roots in Vulgar Latin. The birth of the modern Italian started in Tuscany around the 14th century, and it is mainly attributed to the works of Dante Alighieri, Francesco Petrarca and Giovanni Boccaccio, who are among the most acclaimed authors of the medieval age in Tuscany. However, Italy has been charact...
Conference Paper
Full-text available
In many real world applications, data are characterized by a complex structure, that can be naturally encoded as a graph. In the last years, the popularity of deep learning techniques has renewed the interest in neural models able to process complex patterns. In particular, inspired by the Graph Neural Network (GNN) model, different architectures h...
Conference Paper
Full-text available
In this paper we study a constraint-based representation of neural network architectures. We cast the learning problem in the Lagrangian framework and we investigate a simple optimization procedure that is well suited to fulfil the so-called architectural constraints, learning from the available supervisions. The computational structure of the prop...
Conference Paper
Full-text available
Graph Neural Networks (Scarselli et al., 2009) exploit an iterative diffusion procedure to compute the node states as the fixed point of the train-able state transition function. In this paper, we show how to cast this scheme as a constrained optimization problem, thus avoiding the unfolding procedure required for the computation of the fixed point...
Preprint
Full-text available
Recently, researchers in Machine Learning algorithms, Computer Vision scientists, engineers and others, showed a growing interest in 3D simulators as a mean to artificially create experimental settings that are very close to those in the real world. However, most of the existing platforms to interface algorithms with 3D environments are often desig...
Preprint
Full-text available
Unsupervised learning from continuous visual streams is a challenging problem that cannot be naturally and efficiently managed in the classic batch-mode setting of computation. The information stream must be carefully processed accordingly to an appropriate spatio-temporal distribution of the visual data, while most approaches of learning commonly...
Preprint
Full-text available
Several real-world applications are characterized by data that exhibit a complex structure that can be represented using graphs. The popularity of deep learning techniques renewed the interest in neural architectures able to process these patterns, inspired by the Graph Neural Network (GNN) model. GNNs encode the state of the nodes of the graph by...
Conference Paper
Full-text available
In the last years, the popularity of deep learning techniques has renewed the interest in neural models able to process complex patterns, that are naturally encoded as graphs. In particular, different architectures have been proposed to extend the original Graph Neural Network (GNN) model. GNNs exploit a set of state variables, each assigned to a g...
Preprint
Full-text available
In many real world applications, data are characterized by a complex structure, that can be naturally encoded as a graph. In the last years, the popularity of deep learning techniques has renewed the interest in neural models able to process complex patterns. In particular, inspired by the Graph Neural Network (GNN) model, different architectures h...
Preprint
Full-text available
In this paper we study a constraint-based representation of neural network architectures. We cast the learning problem in the Lagrangian framework and we investigate a simple optimization procedure that is well suited to fulfil the so-called architectural constraints, learning from the available supervisions. The computational structure of the prop...
Preprint
Full-text available
In this paper we describe a video surveillance system able to detect traffic events in videos acquired by fixed videocameras on highways. The events of interest consist in a specific sequence of situations that occur in the video, as for instance a vehicle stopping on the emergency lane. Hence, the detection of these events requires to analyze a te...
Chapter
In this paper we describe a video surveillance system able to detect traffic events in videos acquired by fixed videocameras on highways. The events of interest consist in a specific sequence of situations that occur in the video, as for instance a vehicle stopping on the emergency lane. Hence, the detection of these events requires to analyze a te...
Chapter
Graphs are a natural choice to encode data in many real–world applications. In fact, a graph can describe a given pattern as a complex structure made up of parts (the nodes) and relationships between them (the edges). Despite their rich representational power, most of machine learning approaches cannot deal directly with inputs encoded by graphs. I...

Network

Cited By