753 citations · 3k across the 55 of their papers we have counts for
58 papers
Anti-Collapse Dynamics and the Emergence of Multi-Time-Scale Learning in Recurrent Neural Networks
Lorenzo Livi
Long-range learning is hard for recurrent networks trained with stochastic gradient descent, because the influence of a past input fades with the lag , and if it fades too fa…
Learnability Window in Gated Recurrent Neural Networks
Lorenzo Livi
We develop a statistical theory of temporal learnability in recurrent neural networks, quantifying the maximal temporal horizon over which gradient-based learning c…
Graph State-Space Models and Latent Relational Inference
Daniele Zambon, Andrea Cini, Cesare Alippi
State-space models effectively model multivariate time series by updating over time a representation of the system state from which predictions are made. The state representation i…
Embedding and trajectories of temporal networks
Chanon Thongprayoon, Lorenzo Livi, Naoki Masuda
Temporal network data are increasingly available in various domains, and often represent highly complex systems with intricate structural and temporal evolutions. Due to the diffic…
Transferring Chemical and Energetic Knowledge Between Molecular Systems with Machine Learning
Sajjad Heydari, Stefano Raniolo, Lorenzo Livi +1
Predicting structural and energetic properties of a molecular system is one of the fundamental tasks in molecular simulations, and it has use cases in chemistry, biology, and medic…
Message Passing Neural Networks for Hypergraphs
Sajjad Heydari, Lorenzo Livi
Hypergraph representations are both more efficient and better suited to describe data characterized by relations between two or more objects. In this work, we present a new graph n…
Learning Graph Cellular Automata
Daniele Grattarola, Lorenzo Livi, Cesare Alippi
Cellular automata (CA) are a class of computational models that exhibit rich dynamics emerging from the local interaction of cells arranged in a regular lattice. In this work we fo…
A New Remote Monitor and Control System Based on Sigfox IoT Network
Lorenzo Francesco Livi, Jacopo Catani
We describe a new, low-cost system designed to provide multi-sensor remote condition monitoring of modern scientific laboratories, as well as to allow users to perform actions from…
Flavour-selective localization in interacting lattice fermions via SU(N) symmetry breaking
Daniele Tusi, Lorenzo Franchi, Lorenzo Francesco Livi +10
A large repulsion between particles in a quantum system can lead to their localization, as it happens for the electrons in Mott insulating materials. This paradigm has recently bra…
Learn to Synchronize, Synchronize to Learn
Pietro Verzelli, Cesare Alippi, Lorenzo Livi
In recent years, the machine learning community has seen a continuous growing interest in research aimed at investigating dynamical aspects of both training procedures and machine…
Input-to-State Representation in linear reservoirs dynamics
Pietro Verzelli, Cesare Alippi, Lorenzo Livi +1
Reservoir computing is a popular approach to design recurrent neural networks, due to its training simplicity and approximation performance. The recurrent part of these networks is…
The Echo Index and multistability in input-driven recurrent neural networks
Andrea Ceni, Peter Ashwin, Lorenzo Livi +1
A recurrent neural network (RNN) possesses the echo state property (ESP) if, for a given input sequence, it ``forgets'' any internal states of the driven (nonautonomous) system and…
Recurrence Quantification Analysis of Dynamic Brain Networks
Marinho A. Lopes, Jiaxiang Zhang, Dominik Krzemiński +4
Evidence suggests that brain network dynamics is a key determinant of brain function and dysfunction. Here we propose a new framework to assess the dynamics of brain networks based…
Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling
Filippo Maria Bianchi, Daniele Grattarola, Lorenzo Livi +1
In graph neural networks (GNNs), pooling operators compute local summaries of input graphs to capture their global properties, and they are fundamental for building deep GNNs that…
Graph Random Neural Features for Distance-Preserving Graph Representations
Daniele Zambon, Cesare Alippi, Lorenzo Livi
We present Graph Random Neural Features (GRNF), a novel embedding method from graph-structured data to real vectors based on a family of graph neural networks. The embedding natura…
Autoregressive Models for Sequences of Graphs
Daniele Zambon, Daniele Grattarola, Lorenzo Livi +1
This paper proposes an autoregressive (AR) model for sequences of graphs, which generalises traditional AR models. A first novelty consists in formalising the AR model for a very g…
Echo State Networks with Self-Normalizing Activations on the Hyper-Sphere
Pietro Verzelli, Cesare Alippi, Lorenzo Livi
Among the various architectures of Recurrent Neural Networks, Echo State Networks (ESNs) emerged due to their simplified and inexpensive training procedure. These networks are know…
Deep Divergence-Based Approach to Clustering
Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi +3
A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminati…
Graph Neural Networks with convolutional ARMA filters
Filippo Maria Bianchi, Daniele Grattarola, Lorenzo Livi +1
Popular graph neural networks implement convolution operations on graphs based on polynomial spectral filters. In this paper, we propose a novel graph convolutional layer inspired…
Adversarial Autoencoders with Constant-Curvature Latent Manifolds
Daniele Grattarola, Lorenzo Livi, Cesare Alippi
Constant-curvature Riemannian manifolds (CCMs) have been shown to be ideal embedding spaces in many application domains, as their non-Euclidean geometry can naturally account for s…
Coherent Manipulation of Orbital Feshbach Molecules of Two-Electron Atoms
G. Cappellini, L. F. Livi, L. Franchi +5
Ultracold molecules have experienced increasing attention in recent years. Compared to ultracold atoms, they possess several unique properties that make them perfect candidates for…
A characterization of the Edge of Criticality in Binary Echo State Networks
Pietro Verzelli, Lorenzo Livi, Cesare Alippi
Echo State Networks (ESNs) are simplified recurrent neural network models composed of a reservoir and a linear, trainable readout layer. The reservoir is tunable by some hyper-para…
The Deep Kernelized Autoencoder
Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi +2
Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network. However, it is not always clear what kind of properties of…
Interpreting recurrent neural networks behaviour via excitable network attractors
Andrea Ceni, Peter Ashwin, Lorenzo Livi
Introduction: Machine learning provides fundamental tools both for scientific research and for the development of technologies with significant impact on society. It provides metho…