no code implementations • 9 Apr 2024 • Andrea Zugarini, Kamyar Zeinalipour, Surya Sai Kadali, Marco Maggini, Marco Gori, Leonardo Rigutini
By gathering from Wikipedia pages informative content associated with relevant keywords, we use Large Language Models to automatically generate pedagogical clues related to the given input keyword and its context.
no code implementations • 16 Feb 2024 • Michelangelo Diligenti, Marco Gori, Marco Maggini, Leonardo Rigutini
This paper presents a general framework to integrate prior knowledge in the form of logic constraints among a set of task functions into kernel machines.
no code implementations • 12 Feb 2024 • Matteo Tiezzi, Michele Casoni, Alessandro Betti, Tommaso Guidi, Marco Gori, Stefano Melacci
A longstanding challenge for the Machine Learning community is the one of developing models that are capable of processing and learning from very long sequences of data.
no code implementations • 4 Feb 2024 • Alessandro Betti, Marco Gori
The spectacular results achieved in machine learning, including the recent advances in generative AI, rely on large data collections.
no code implementations • 14 Dec 2023 • Alessandro Betti, Michele Casoni, Marco Gori, Simone Marullo, Stefano Melacci, Matteo Tiezzi
This paper introduces a novel neural-based approach to optimal control, with the aim of working forward-in-time.
no code implementations • 3 Dec 2023 • Kamyar Zeinalipour, Mohamed Zaky Saad, Marco Maggini, Marco Gori
This paper presents the first Arabic crossword puzzle generator driven by advanced AI technology.
no code implementations • 27 Nov 2023 • Giovanni Angelini, Marco Ernandes, Tommaso laquinta, Caroline Stehlé, Fanny Simões, Kamyar Zeinalipour, Andrea Zugarini, Marco Gori
Crossword puzzles are one of the most popular word games, played in different languages all across the world, where riddle style can vary significantly from one country to another.
no code implementations • 27 Nov 2023 • Kamyar Zeinalipour, Tommaso laquinta, Asya Zanollo, Giovanni Angelini, Leonardo Rigutini, Marco Maggini, Marco Gori
On the other hand, for generating crossword clues from a given text, Zero/Few-shot learning techniques were used to extract clues from the input text, adding variety and creativity to the puzzles.
no code implementations • 6 Nov 2023 • Michelangelo Diligenti, Marco Gori, Marco Maggini, Leonardo Rigutini
In this paper we propose a general framework to integrate supervised and unsupervised examples with background knowledge expressed by a collection of first-order logic clauses into kernel machines.
no code implementations • 2 Nov 2023 • Kamyar Zeinalipour, Marco Gori
While ECG situations have numerous similarities, little attention has been paid to categorizing ECGs using graph neural networks.
no code implementations • 13 Sep 2023 • Marco Gori, Stefano Melacci
By and large, the professional handling of huge data collections is regarded as a fundamental ingredient of the progress of machine learning and of its spectacular results in related disciplines, with a growing agreement on risks connected to the centralization of such data collections.
no code implementations • 5 Jun 2023 • Simone Marullo, Matteo Tiezzi, Marco Gori, Stefano Melacci, Tinne Tuytelaars
The intrinsic difficulty in adapting deep learning models to non-stationary environments limits the applicability of neural networks to real-world tasks.
1 code implementation • 17 Oct 2022 • Enrico Meloni, Lapo Faggi, Simone Marullo, Alessandro Betti, Matteo Tiezzi, Marco Gori, Stefano Melacci
nature of the streamed data with samples that are smoothly evolving over time for efficient gradient computations.
no code implementations • 8 Aug 2022 • Andrea Panizza, Szymon Tomasz Stefanek, Stefano Melacci, Giacomo Veneri, Marco Gori
The application is challenging due to the large image resolutions in which defects are very small and hardly captured by the commonly used anchor sizes, and also due to the small size of the available dataset.
no code implementations • 30 Jun 2022 • Alessandro Betti, Marco Gori, Stefano Melacci
The remarkable progress in computer vision over the last few years is, by and large, attributed to deep learning, fueled by the availability of huge sets of labeled data, and paired with the explosive growth of the GPU paradigm.
1 code implementation • 15 Oct 2021 • Gabriele Ciravegna, Frédéric Precioso, Alessandro Betti, Kevin Mottin, Marco Gori
The deployment of Deep Learning (DL) models is still precluded in those contexts where the amount of supervised data is limited.
no code implementations • 13 Oct 2021 • Nicola Picchiotti, Marco Gori
In recent years, Artificial Intelligence (AI) algorithms have been proven to outperform traditional statistical methods in terms of predictivity, especially when a large amount of data was available.
1 code implementation • 13 Oct 2021 • Nicola Picchiotti, Marco Gori
Amongst others, the adoption of Rectified Linear Units (ReLUs) is regarded as one of the ingredients of the success of deep learning.
no code implementations • 12 Oct 2021 • Alessandro Betti, Marco Gori, Stefano Melacci, Marcello Pelillo, Fabio Roli
This paper sustains the position that the time has come for thinking of learning machines that conquer visual skills in a truly human-like context, where a few human-like object supervisions are given by vocal interactions and pointing aids only.
no code implementations • 21 Sep 2021 • Matteo Tiezzi, Gabriele Ciravegna, Marco Gori
Graph Drawing techniques have been developed in the last few years with the purpose of producing aesthetically pleasing node-link layouts.
1 code implementation • 17 Sep 2021 • Enrico Meloni, Matteo Tiezzi, Luca Pasqualini, Marco Gori, Stefano Melacci
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.
1 code implementation • 11 Aug 2021 • Gabriele Ciravegna, Pietro Barbiero, Francesco Giannini, Marco Gori, Pietro Lió, Marco Maggini, Stefano Melacci
The language used to communicate the explanations must be formal enough to be implementable in a machine and friendly enough to be understandable by a wide audience.
no code implementations • 21 Jun 2021 • Simone Marullo, Matteo Tiezzi, Marco Gori, Stefano Melacci
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.
3 code implementations • 12 Jun 2021 • Pietro Barbiero, Gabriele Ciravegna, Francesco Giannini, Pietro Lió, Marco Gori, Stefano Melacci
Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains.
Ranked #1 on Image Classification on CUB
1 code implementation • 28 Oct 2020 • Andrea Zugarini, Enrico Meloni, Alessandro Betti, Andrea Panizza, Marco Corneli, Marco Gori
We formulate the problem in terms of a functional risk that depends on the learning variables through the solutions of a dynamic system.
no code implementations • 15 Sep 2020 • Dario Zanca, Marco Gori, Stefano Melacci, Alessandra Rufa
Another where the information from these maps is merged in order to select a single location to be attended for further and more complex computations and reasoning.
no code implementations • 1 Sep 2020 • Alessandro Betti, Marco Gori, Simone Marullo, Stefano Melacci
In this paper we present a foundational study on a constrained method that defines learning problems with Neural Networks in the context of the principle of least cognitive action, which very much resembles the principle of least action in mechanics.
1 code implementation • 16 Jul 2020 • Enrico Meloni, Luca Pasqualini, Matteo Tiezzi, Marco Gori, Stefano Melacci
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.
no code implementations • 19 Jun 2020 • Lapo Faggi, Alessandro Betti, Dario Zanca, Stefano Melacci, Marco Gori
Fast reactions to changes in the surrounding visual environment require efficient attention mechanisms to reallocate computational resources to most relevant locations in the visual field.
no code implementations • NeurIPS 2020 • Matteo Tiezzi, Stefano Melacci, Alessandro Betti, Marco Maggini, Marco Gori
In order to better structure the input probability distribution, we use a human-like focus of attention model that, coherently with the information maximization model, is also based on second-order differential equations.
no code implementations • 6 Jun 2020 • Stefano Melacci, Gabriele Ciravegna, Angelo Sotgiu, Ambra Demontis, Battista Biggio, Marco Gori, Fabio Roli
Adversarial attacks on machine learning-based classifiers, along with defense mechanisms, have been widely studied in the context of single-label classification problems.
no code implementations • 29 Feb 2020 • Luis C. Lamb, Artur Garcez, Marco Gori, Marcelo Prates, Pedro Avelar, Moshe Vardi
Neural-symbolic computing has now become the subject of interest of both academic and industry research laboratories.
no code implementations • 18 Feb 2020 • Giuseppe Marra, Matteo Tiezzi, Stefano Melacci, Alessandro Betti, Marco Maggini, Marco Gori
In this paper we study a constraint-based representation of neural network architectures.
1 code implementation • 18 Feb 2020 • Matteo Tiezzi, Giuseppe Marra, Stefano Melacci, Marco Maggini, Marco Gori
GNNs exploit a set of state variables, each assigned to a graph node, and a diffusion mechanism of the states among neighbor nodes, to implement an iterative procedure to compute the fixed point of the (learnable) state transition function.
no code implementations • 11 Feb 2020 • Dario Zanca, Stefano Melacci, Marco Gori
A computational modeling of this phenomenon must take into account where people look in order to evaluate which are the salient locations (spatial distribution of the fixations), when they look in those locations to understand the temporal development of the exploration (temporal order of the fixations), and how they move from one location to another with respect to the dynamics of the scene and the mechanics of the eyes (dynamics).
no code implementations • 6 Feb 2020 • Giuseppe Marra, Michelangelo Diligenti, Francesco Giannini, Marco Gori, Marco Maggini
Deep learning has been shown to achieve impressive results in several tasks where a large amount of training data is available.
no code implementations • 10 Dec 2019 • Alessandro Betti, Marco Gori
The Backpropagation algorithm relies on the abstraction of using a neural model that gets rid of the notion of time, since the input is mapped instantaneously to the output.
no code implementations • 21 Nov 2019 • Pedro H. C. Avelar, Anderson R. Tavares, Marco Gori, Luis C. Lamb
In this paper we propose the use of continuous residual modules for graph kernels in Graph Neural Networks.
no code implementations • 24 Sep 2019 • Lisa Graziani, Stefano Melacci, Marco Gori
In this paper we focus on Facebook posts paired with reactions of multiple users, and we investigate their relationships with classes of emotions that are typically considered in the task of emotion detection.
no code implementations • 1 Sep 2019 • Alessandro Betti, Marco Gori, Stefano Melacci
Humans are continuously exposed to a stream of visual data with a natural temporal structure.
no code implementations • 26 Jul 2019 • Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Marco Maggini, Marco Gori
Neural-symbolic approaches have recently gained popularity to inject prior knowledge into a learner without requiring it to induce this knowledge from data.
no code implementations • 18 Jul 2019 • Francesco Giannini, Giuseppe Marra, Michelangelo Diligenti, Marco Maggini, Marco Gori
Deep learning has been shown to achieve impressive results in several domains like computer vision and natural language processing.
no code implementations • 14 Jul 2019 • Alessandro Betti, Marco Gori
By and large the process of learning concepts that are embedded in time is regarded as quite a mature research topic.
no code implementations • 11 Jul 2019 • Alessandro Betti, Marco Gori
This paper proposes an in-depth re-thinking of neural computation that parallels apparently unrelated laws of physics, that are formulated in the variational framework of the least action principle.
no code implementations • 4 Jul 2019 • Alessandro Betti, Marco Gori
Machine Learning algorithms are typically regarded as appropriate optimization schemes for minimizing risk functions that are constructed on the training set, which conveys statistical flavor to the corresponding learning problem.
no code implementations • 15 May 2019 • Artur d'Avila Garcez, Marco Gori, Luis C. Lamb, Luciano Serafini, Michael Spranger, Son N. Tran
In spite of the recent impact of AI, several works have identified the need for principled knowledge representation and reasoning mechanisms integrated with deep learning-based systems to provide sound and explainable models for such systems.
no code implementations • 18 Mar 2019 • Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Marco Gori
In spite of the amazing results obtained by deep learning in many applications, a real intelligent behavior of an agent acting in a complex environment is likely to require some kind of higher-level symbolic inference.
2 code implementations • 23 Jan 2019 • Marcelo O. R. Prates, Pedro H. C. Avelar, Henrique Lemos, Marco Gori, Luis Lamb
To illustrate the generality of the original model, we present a Graph Neural Network formalisation, which partitions the vertices of a graph into a number of types.
no code implementations • 14 Jan 2019 • Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Marco Gori
Deep learning is very effective at jointly learning feature representations and classification models, especially when dealing with high dimensional input patterns.
no code implementations • 28 Aug 2018 • Alessandro Betti, Marco Gori, Stefano Melacci
A special choice of the functional index, which leads to forth-order differential equations---Cognitive Action Laws (CAL)---exhibits a structure that mirrors classic formulation of machine learning.
no code implementations • 21 Aug 2018 • Alessandro Betti, Marco Gori, Giuseppe Marra
This might open the doors to a truly novel class of learning algorithms where, because of the introduction of the notion of support neurons, the optimization scheme also plays a fundamental role in the construction of the architecture.
no code implementations • ICLR 2019 • Giuseppe Marra, Dario Zanca, Alessandro Betti, Marco Gori
The effectiveness of deep neural architectures has been widely supported in terms of both experimental and foundational principles.
no code implementations • 16 Jul 2018 • Giuseppe Marra, Francesco Giannini, Michelangelo Diligenti, Marco Gori
We use deep architectures to model the involved variables, and propose a computational scheme where the learning process carries out a satisfaction of the constraints.
no code implementations • 14 Jul 2018 • Giovanni Bellettini, Alessandro Betti, Marco Gori
By and large the behavior of stochastic gradient is regarded as a challenging problem, and it is often presented in the framework of statistical machine learning.
no code implementations • 14 Jul 2018 • Alessandro Betti, Marco Gori, Stefano Melacci
The puzzle of computer vision might find new challenging solutions when we realize that most successful methods are working at image level, which is remarkably more difficult than processing directly visual streams, just as happens in nature.
no code implementations • 16 Jan 2018 • Alessandro Betti, Marco Gori
Basically, while the theory enables the implementation of novel computer vision systems, it is also provides an intriguing explanation of the solution that evolution has discovered for humans, where it looks like that the video blurring in newborns and the day-night rhythm seem to emerge in a general computational framework, regardless of biology.
1 code implementation • NeurIPS 2017 • Dario Zanca, Marco Gori
We devise variational laws of the eye-movement that rely on a generalized view of the Least Action Principle in physics.
Ranked #1 on Saliency Detection on CAT2000
no code implementations • 9 Jan 2017 • Marco Gori, Marco Maggini, Alessandro Rossi
In this document we shows a first implementation and some preliminary results of a new theory, facing Machine Learning problems in the frameworks of Classical Mechanics and Variational Calculus.
no code implementations • 3 Jan 2017 • Marco Gori, Marco Maggini, Alessandro Rossi
We analyze a new approach to Machine Learning coming from a modification of classical regularization networks by casting the process in the time dimension, leading to a sort of collapse of dimensionality in the problem of learning the model parameters.
no code implementations • 11 Aug 2014 • Marco Gori, Marco Lippi, Marco Maggini, Stefano Melacci
In the last few years we have seen a growing interest in machine learning approaches to computer vision and, especially, to semantic labeling.