Search Results for author: Alessandro Betti

Found 33 papers, 4 papers with code

On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era

no code implementations12 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.

Nature-Inspired Local Propagation

no code implementations4 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.

Neural Time-Reversed Generalized Riccati Equation

no code implementations14 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.

PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks

1 code implementation17 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.

Deep Learning to See: Towards New Foundations of Computer Vision

no code implementations30 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.

BIG-bench Machine Learning

Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams

1 code implementation26 Apr 2022 Matteo Tiezzi, Simone Marullo, Lapo Faggi, Enrico Meloni, Alessandro Betti, Stefano Melacci

Our experiments leverage 3D virtual environments and they show that the proposed agents can learn to distinguish objects just by observing the video stream.

A lightweight and accurate YOLO-like network for small target detection in Aerial Imagery

no code implementations5 Apr 2022 Alessandro Betti

Despite the breakthrough deep learning performances achieved for automatic object detection, small target detection is still a challenging problem, especially when looking at fast and accurate solutions suitable for mobile or edge applications.

Benchmarking object-detection +2

A Multi-Stage model based on YOLOv3 for defect detection in PV panels based on IR and Visible Imaging by Unmanned Aerial Vehicle

no code implementations23 Nov 2021 Antonio Di Tommaso, Alessandro Betti, Giacomo Fontanelli, Benedetto Michelozzi

As solar capacity installed worldwide continues to grow, there is an increasing awareness that advanced inspection systems are becoming of utmost importance to schedule smart interventions and minimize downtime likelihood.

Defect Detection

Knowledge-driven Active Learning

1 code implementation15 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.

Active Learning Multi-Label Classification +2

Can machines learn to see without visual databases?

no code implementations12 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.

Position

Evaluating Continual Learning Algorithms by Generating 3D Virtual Environments

no code implementations16 Sep 2021 Enrico Meloni, Alessandro Betti, Lapo Faggi, Simone Marullo, Matteo Tiezzi, Stefano Melacci

However, in order to devise continual learning algorithms that operate in more realistic conditions, it is fundamental to gain access to rich, fully customizable and controlled experimental playgrounds.

Continual Learning

An Optimal Control Approach to Learning in SIDARTHE Epidemic model

1 code implementation28 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.

Developing Constrained Neural Units Over Time

no code implementations1 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.

Wave Propagation of Visual Stimuli in Focus of Attention

no code implementations19 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.

Scanpath prediction

Focus of Attention Improves Information Transfer in Visual Features

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.

Local Propagation in Constraint-based Neural Network

no code implementations18 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.

Real-Time target detection in maritime scenarios based on YOLOv3 model

no code implementations10 Feb 2020 Alessandro Betti, Benedetto Michelozzi, Andrea Bracci, Andrea Masini

In this work a novel ships dataset is proposed consisting of more than 56k images of marine vessels collected by means of web-scraping and including 12 ship categories.

Backprop Diffusion is Biologically Plausible

no code implementations10 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.

Condition monitoring and early diagnostics methodologies for hydropower plants

no code implementations13 Nov 2019 Alessandro Betti, Emanuele Crisostomi, Gianluca Paolinelli, Antonio Piazzi, Fabrizio Ruffini, Mauro Tucci

Hydropower plants are one of the most convenient option for power generation, as they generate energy exploiting a renewable source, they have relatively low operating and maintenance costs, and they may be used to provide ancillary services, exploiting the large reservoirs of available water.

A Scalable Predictive Maintenance Model for Detecting Wind Turbine Component Failures Based on SCADA Data

no code implementations22 Oct 2019 Lorenzo Gigoni, Alessandro Betti, Mauro Tucci, Emanuele Crisostomi

In this work, a novel predictive maintenance system is presented and applied to the main components of wind turbines.

A Machine Learning Model for Long-Term Power Generation Forecasting at Bidding Zone Level

no code implementations8 Oct 2019 Michela Moschella, Mauro Tucci, Emanuele Crisostomi, Alessandro Betti

The increasing penetration level of energy generation from renewable sources is demanding for more accurate and reliable forecasting tools to support classic power grid operations (e. g., unit commitment, electricity market clearing or maintenance planning).

BIG-bench Machine Learning

Learning Visual Features Under Motion Invariance

no code implementations1 Sep 2019 Alessandro Betti, Marco Gori, Stefano Melacci

Humans are continuously exposed to a stream of visual data with a natural temporal structure.

On the Role of Time in Learning

no code implementations14 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.

Spatiotemporal Local Propagation

no code implementations11 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.

Least Action Principles and Well-Posed Learning Problems

no code implementations4 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.

Day-Ahead Hourly Forecasting of Power Generation from Photovoltaic Plants

no code implementations26 Feb 2019 Lorenzo Gigoni, Alessandro Betti, Emanuele Crisostomi, Alessandro Franco, Mauro Tucci, Fabrizio Bizzarri, Debora Mucci

The ability to accurately forecast power generation from renewable sources is nowadays recognised as a fundamental skill to improve the operation of power systems.

Cognitive Action Laws: The Case of Visual Features

no code implementations28 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.

BIG-bench Machine Learning

Backpropagation and Biological Plausibility

no code implementations21 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.

Learning Neuron Non-Linearities with Kernel-Based Deep Neural Networks

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.

Motion Invariance in Visual Environments

no code implementations14 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.

Generalization in quasi-periodic environments

no code implementations14 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.

Convolutional Networks in Visual Environments

no code implementations16 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.

Cannot find the paper you are looking for? You can Submit a new open access paper.