Search Results for author: Lorenzo Livi

Found 39 papers, 10 papers with code

Graph state-space models

no code implementations4 Jan 2023 Daniele Zambon, Andrea Cini, Lorenzo Livi, Cesare Alippi

State-space models constitute an effective modeling tool to describe multivariate time series and operate by maintaining an updated representation of the system state from which predictions are made.

Time Series

Transferring Chemical and Energetic Knowledge Between Molecular Systems with Machine Learning

no code implementations6 May 2022 Sajjad Heydari, Stefano Raniolo, Lorenzo Livi, Vittorio Limongelli

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 medicine.

BIG-bench Machine Learning Transfer Learning

Message Passing Neural Networks for Hypergraphs

no code implementations31 Mar 2022 Sajjad Heydari, Lorenzo Livi

Hypergraph representations are both more efficient and better suited to describe data characterized by relations between two or more objects.

Hypergraph representations Node Classification

Learning Graph Cellular Automata

1 code implementation NeurIPS 2021 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.

Learn to Synchronize, Synchronize to Learn

no code implementations6 Oct 2020 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 learning models.

BIG-bench Machine Learning

Input-to-State Representation in linear reservoirs dynamics

no code implementations24 Mar 2020 Pietro Verzelli, Cesare Alippi, Lorenzo Livi, Peter Tino

Reservoir computing is a popular approach to design recurrent neural networks, due to its training simplicity and approximation performance.

Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling

1 code implementation24 Oct 2019 Filippo Maria Bianchi, Daniele Grattarola, Lorenzo Livi, Cesare Alippi

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 learn hierarchical representations.

Graph Classification Representation Learning

Graph Random Neural Features for Distance-Preserving Graph Representations

1 code implementation ICML 2020 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.

Echo State Networks with Self-Normalizing Activations on the Hyper-Sphere

1 code implementation27 Mar 2019 Pietro Verzelli, Cesare Alippi, Lorenzo Livi

Finding such a region requires searching in hyper-parameter space in a sensible way: hyper-parameter configurations marginally outside such a region might yield networks exhibiting fully developed chaos, hence producing unreliable computations.

Autoregressive Models for Sequences of Graphs

2 code implementations18 Mar 2019 Daniele Zambon, Daniele Grattarola, Lorenzo Livi, Cesare Alippi

This paper proposes an autoregressive (AR) model for sequences of graphs, which generalises traditional AR models.

Deep Divergence-Based Approach to Clustering

no code implementations13 Feb 2019 Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi, Lorenzo Livi, Arnt-Børre Salberg, Robert Jenssen

A promising direction in deep learning research consists in learning representations and simultaneously discovering cluster structure in unlabeled data by optimizing a discriminative loss function.

Deep Clustering

Adversarial Autoencoders with Constant-Curvature Latent Manifolds

1 code implementation11 Dec 2018 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 some relevant properties of data, like hierarchy and circularity.

Link Prediction

A characterization of the Edge of Criticality in Binary Echo State Networks

no code implementations3 Oct 2018 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.

Interpreting recurrent neural networks behaviour via excitable network attractors

no code implementations27 Jul 2018 Andrea Ceni, Peter Ashwin, Lorenzo Livi

Simulations conducted on a controlled benchmark task confirm the relevance of these attractors for interpreting the behaviour of recurrent neural networks, at least for tasks that involve learning a finite number of stable states and transitions between them.

BIG-bench Machine Learning

The Deep Kernelized Autoencoder

no code implementations19 Jul 2018 Michael Kampffmeyer, Sigurd Løkse, Filippo M. Bianchi, Robert Jenssen, Lorenzo Livi

Autoencoders learn data representations (codes) in such a way that the input is reproduced at the output of the network.

Denoising

Change Point Methods on a Sequence of Graphs

no code implementations18 May 2018 Daniele Zambon, Cesare Alippi, Lorenzo Livi

Given a finite sequence of graphs, e. g., coming from technological, biological, and social networks, the paper proposes a methodology to identify possible changes in stationarity in the stochastic process generating the graphs.

Graph Classification Seizure Detection

Change Detection in Graph Streams by Learning Graph Embeddings on Constant-Curvature Manifolds

1 code implementation16 May 2018 Daniele Grattarola, Daniele Zambon, Cesare Alippi, Lorenzo Livi

A common approach is to use embedding techniques to represent graphs as points in a conventional Euclidean space, but non-Euclidean spaces have often been shown to be better suited for embedding graphs.

Change Detection Seizure Detection

Anomaly and Change Detection in Graph Streams through Constant-Curvature Manifold Embeddings

no code implementations3 May 2018 Daniele Zambon, Lorenzo Livi, Cesare Alippi

The proposed methodology consists in embedding graphs into a geometric space and perform change detection there by means of conventional methods for numerical streams.

Anomaly Detection Change Detection

Time series kernel similarities for predicting Paroxysmal Atrial Fibrillation from ECGs

no code implementations21 Jan 2018 Filippo Maria Bianchi, Lorenzo Livi, Alberto Ferrante, Jelena Milosevic, Miroslaw Malek

We tackle the problem of classifying Electrocardiography (ECG) signals with the aim of predicting the onset of Paroxysmal Atrial Fibrillation (PAF).

Classification Electrocardiography (ECG) +2

Concept Drift and Anomaly Detection in Graph Streams

1 code implementation21 Jun 2017 Daniele Zambon, Cesare Alippi, Lorenzo Livi

Graph representations offer powerful and intuitive ways to describe data in a multitude of application domains.

Anomaly Detection Change Detection

Deep Kernelized Autoencoders

no code implementations8 Feb 2017 Michael Kampffmeyer, Sigurd Løkse, Filippo Maria Bianchi, Robert Jenssen, Lorenzo Livi

In this paper we introduce the deep kernelized autoencoder, a neural network model that allows an explicit approximation of (i) the mapping from an input space to an arbitrary, user-specified kernel space and (ii) the back-projection from such a kernel space to input space.

Denoising

Multiplex visibility graphs to investigate recurrent neural networks dynamics

no code implementations10 Sep 2016 Filippo Maria Bianchi, Lorenzo Livi, Cesare Alippi, Robert Jenssen

We show that topological properties of such a multiplex reflect important features of RNN dynamics and are used to guide the tuning procedure.

Time Series

One-class classifiers based on entropic spanning graphs

no code implementations8 Apr 2016 Lorenzo Livi, Cesare Alippi

The final partition is derived by exploiting a criterion based on mutual information minimization.

One-class classifier

Determination of the edge of criticality in echo state networks through Fisher information maximization

no code implementations11 Mar 2016 Lorenzo Livi, Filippo Maria Bianchi, Cesare Alippi

In this paper, we aim at addressing this issue by proposing a theoretically motivated, unsupervised method based on Fisher information for determining the edge of criticality in recurrent neural networks.

Investigating echo state networks dynamics by means of recurrence analysis

no code implementations26 Jan 2016 Filippo Maria Bianchi, Lorenzo Livi, Cesare Alippi

We verify that the determination of the edge of stability provided by such RQA measures is more accurate than two well-known criteria based on the Jacobian matrix of the reservoir.

Time Series Time Series Analysis

Data-driven detrending of nonstationary fractal time series with echo state networks

1 code implementation24 Oct 2015 Enrico Maiorino, Filippo Maria Bianchi, Lorenzo Livi, Antonello Rizzi, Alireza Sadeghian

We assume that such a dynamical process is predictable to a certain degree by means of a class of recurrent networks called Echo State Network (ESN), which are capable to model a generic dynamical process.

Time Series

Discrimination and characterization of Parkinsonian rest tremors by analyzing long-term correlations and multifractal signatures

no code implementations10 Apr 2015 Lorenzo Livi, Alireza Sadeghian, Hamid Sadeghian

The subjects belong to two different groups, formed by four and eight subjects with, respectively, high- and low-amplitude rest tremors.

General Classification

On the impact of topological properties of smart grids in power losses optimization problems

no code implementations19 Jan 2015 Francesca Possemato, Maurizio Paschero, Lorenzo Livi, Antonello Rizzi, Alireza Sadeghian

In this paper, we face the problem of joint optimization of both topology and network parameters in a real smart grid.

Building pattern recognition applications with the SPARE library

no code implementations20 Oct 2014 Lorenzo Livi, Guido Del Vescovo, Antonello Rizzi, Fabio Massimo Frattale Mascioli

This paper presents the SPARE C++ library, an open source software tool conceived to build pattern recognition and soft computing systems.

General Classification

An Agent-Based Algorithm exploiting Multiple Local Dissimilarities for Clusters Mining and Knowledge Discovery

no code implementations17 Sep 2014 Filippo Maria Bianchi, Enrico Maiorino, Lorenzo Livi, Antonello Rizzi, Alireza Sadeghian

We propose a multi-agent algorithm able to automatically discover relevant regularities in a given dataset, determining at the same time the set of configurations of the adopted parametric dissimilarity measure yielding compact and separated clusters.

Designing labeled graph classifiers by exploiting the Rényi entropy of the dissimilarity representation

no code implementations22 Aug 2014 Lorenzo Livi

Representing patterns as labeled graphs is becoming increasingly common in the broad field of computational intelligence.

General Classification

Classifying sequences by the optimized dissimilarity space embedding approach: a case study on the solubility analysis of the E. coli proteome

no code implementations17 Aug 2014 Lorenzo Livi, Antonello Rizzi, Alireza Sadeghian

We evaluate a version of the recently-proposed classification system named Optimized Dissimilarity Space Embedding (ODSE) that operates in the input space of sequences of generic objects.

Classification General Classification +1

Characterization of graphs for protein structure modeling and recognition of solubility

no code implementations30 Jul 2014 Lorenzo Livi, Alessandro Giuliani, Alireza Sadeghian

This paper deals with the relations among structural, topological, and chemical properties of the E. Coli proteome from the vantage point of the solubility/aggregation propensity of proteins.

One-class classifier

Entropic one-class classifiers

no code implementations28 Jul 2014 Lorenzo Livi, Alireza Sadeghian, Witold Pedrycz

The one-class classification problem is a well-known research endeavor in pattern recognition.

Anomaly Detection General Classification +1

Toward a multilevel representation of protein molecules: comparative approaches to the aggregation/folding propensity problem

no code implementations28 Jul 2014 Lorenzo Livi, Alessandro Giuliani, Antonello Rizzi

This paper builds upon the fundamental work of Niwa et al. [34], which provides the unique possibility to analyze the relative aggregation/folding propensity of the elements of the entire Escherichia coli (E. coli) proteome in a cell-free standardized microenvironment.

Data granulation by the principles of uncertainty

no code implementations26 Jul 2014 Lorenzo Livi, Alireza Sadeghian

The proposed framework is conceived (i) to offer a guideline for the synthesis of information granules and (ii) to build a groundwork to compare and quantitatively judge over different data granulation procedures.

Modeling and Recognition of Smart Grid Faults by a Combined Approach of Dissimilarity Learning and One-Class Classification

no code implementations25 Jul 2014 Enrico De Santis, Lorenzo Livi, Alireza Sadeghian, Antonello Rizzi

Modern electric power grids (smart grids) are equipped with smart sensors that allow to gather real-time information regarding the physical status of all the component elements belonging to the whole infrastructure (e. g., cables and related insulation, transformers, breakers and so on).

General Classification One-class classifier

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