6 citations · 35 across the 25 of their papers we have counts for
31 papers
Least-time Gradient Flow
Alessandro Betti, Marco Gori, Stefano Melacci +1
Prescribing the speed of gradient flow on the risk itself, by the dynamics $\dot w=-u(E(w))\nabla E(w)/\abs{\nabla E(w)}^{2}$, makes the risk obey exa…
Generative System Dynamics in Recurrent Neural Networks
Michele Casoni, Tommaso Guidi, Alessandro Betti +2
In this study, we investigate the continuous time dynamics of Recurrent Neural Networks (RNNs), focusing on systems with nonlinear activation functions. The objective of this work…
A Unified Framework for Neural Computation and Learning Over Time
Stefano Melacci, Alessandro Betti, Michele Casoni +3
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 manne…
Dynamic Decoupling of Placid Terminal Attractor-based Gradient Descent Algorithm
Jinwei Zhao, Marco Gori, Alessandro Betti +4
Gradient descent (GD) and stochastic gradient descent (SGD) have been widely used in a large number of application domains. Therefore, understanding the dynamics of GD and improvin…
State-Space Modeling in Long Sequence Processing: A Survey on Recurrence in the Transformer Era
Matteo Tiezzi, Michele Casoni, Alessandro Betti +2
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 re…
On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era
Matteo Tiezzi, Michele Casoni, Alessandro Betti +3
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. The outsta…
Nature-Inspired Local Propagation
Alessandro Betti, Marco Gori
The spectacular results achieved in machine learning, including the recent advances in generative AI, rely on large data collections. On the opposite, intelligent processes in natu…
Neural Time-Reversed Generalized Riccati Equation
Alessandro Betti, Michele Casoni, Marco Gori +3
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 sol…
Forward Approximate Solution for Linear Quadratic Tracking
Alessandro Betti, Michele Casoni, Marco Gori
In this paper, we discuss an approximation strategy for solving the Linear Quadratic Tracking that is both forward and local in time. We exploit the known form of the value functio…
PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks
Enrico Meloni, Lapo Faggi, Simone Marullo +4
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 stream…
Deep Learning to See: Towards New Foundations of Computer Vision
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 paire…
Stochastic Coherence Over Attention Trajectory For Continuous Learning In Video Streams
Matteo Tiezzi, Simone Marullo, Lapo Faggi +3
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 p…
Can machines learn to see without visual databases?
Alessandro Betti, Marco Gori, Stefano Melacci +2
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 su…
Evaluating Continual Learning Algorithms by Generating 3D Virtual Environments
Enrico Meloni, Alessandro Betti, Lapo Faggi +3
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 ch…
An Optimal Control Approach to Learning in SIDARTHE Epidemic model
Andrea Zugarini, Enrico Meloni, Alessandro Betti +3
The COVID-19 outbreak has stimulated the interest in the proposal of novel epidemiological models to predict the course of the epidemic so as to help planning effective control str…
Developing Constrained Neural Units Over Time
Alessandro Betti, Marco Gori, Simone Marullo +1
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,…
Wave Propagation of Visual Stimuli in Focus of Attention
Lapo Faggi, Alessandro Betti, Dario Zanca +2
Fast reactions to changes in the surrounding visual environment require efficient attention mechanisms to reallocate computational resources to most relevant locations in the visua…
Focus of Attention Improves Information Transfer in Visual Features
Matteo Tiezzi, Stefano Melacci, Alessandro Betti +2
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…
Local Propagation in Constraint-based Neural Network
Giuseppe Marra, Matteo Tiezzi, Stefano Melacci +3
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 optim…
Backprop Diffusion is Biologically Plausible
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. In thi…
Learning Visual Features Under Motion Invariance
Alessandro Betti, Marco Gori, Stefano Melacci
Humans are continuously exposed to a stream of visual data with a natural temporal structure. However, most successful computer vision algorithms work at image level, completely di…
On the Role of Time in Learning
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. Hidden Markov models, recurrent neural networks are, amongst o…
Spatiotemporal Local Propagation
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…
Least Action Principles and Well-Posed Learning Problems
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 statist…