The CIML (Computational Intelligence and Machine Learning) group at the department of Computer Science of the University of Pisa has experience in Artificial Intelligence methodologies, ranging from Computational Intelligence to Machine Learning approaches such as Neural Networks, Deep Learning, Probabilistic Learning, Signal and Image processing, and other Pattern Recognition techniques, with an international scientific leadership in topics for Learning in Structured Domains (sequences, trees and graphs/networks). This knowledge led to the development of new methodologies which have been exploited for the design of successful systems in different interdisciplinary application domains.

Spotlight News

Special Issue (2020/2021) on "Deep Neural Networks for Graphs: Theory, Models, Algorithms and Applications" - IEEE Transaction on Neural Networks and Learning Systems: PDF of the call. Read More

Special Issue (2020) on "New Frontiers in Extremely Efficient Reservoir Computing" - IEEE Transaction on Neural Networks and Learning Systems: PDF of the call. Read More

Special Issue (2020) on Trends in Reservoir Computing - Cognitive Computation. Call for papers.

"Prediction of Dynamical Properties of Biochemical Pathways with Graph Neural Networks" @ BIOSTEC 2020 (Bioinformatics 2020) won the best paper award !

Research Activities

Since the 90's the research of the CIML group addresses the development of new Machine Learning methodologies and the analysis of their computational properties. The research is aimed at defining frameworks for the development of intelligent systems and intelligent data analysis tools for learning in structured domains (sequences, trees, graphs) and for the application to innovative interdisciplinary fields.

The design of new learning algorithms includes Neural Networks, Probabilistic models, Reservoir Computing models, Deep Learning approaches, Kernel-based methods, Support Vector Machines, and other Pattern Recognition techniques, with an international scientific leadership in topics for adaptive processing of structured data.

The application fields include Medicine/Health care, BioInformatics, ChemInformatics, Robotics, Intelligent Wireless Sensor Networks, and Signal/Image Processing.

The Group has participated in several EU and national funded projects.


Learning in Structured Domains

Deep Neural Networks

Reservoir Computing

Probabilistic Models

Kernel Methods


Intelligent Data Analysis

ChemInformatics (QSPR/QSAR, Toxicology)


Health/biomedical Informatics

Robotics and Wireless Sensor Networks

Signal and Image Analysis

Intelligent/Adaptive Sensor Networks

Ambient Assisted Living

Parallel Computing

Human Activity Recognition


Alessio Micheli

Associate Professor, Head of CIML

Davide Bacciu

Associate Professor

Claudio Gallicchio

Assistant Professor

Vincenzo Lomonaco

Assistant Professor

Lucia Passaro

Assistant Professor

Antonio Carta

Post-Doc Researcher

Daniele Castellana

Post-Doc Researcher

Giovanna Maria Dimitri

Post-doc Researcher

Marco Podda

Post-Doc Researcher

Andrea Cossu

PhD Student

Valerio De Caro

PhD Student

Federico Errica

PhD Student

Alessio Gravina

PhD Student

Francesco Landolfi

PhD Student

Danilo Numeroso

PhD Student

Michele Resta

PhD Student

Asma Sattar

PhD Student

Domenico Tortorella

PhD Student

Andrea Valenti

PhD Student

Past Members

Antonina Starita

Full Professor

Umberto Barcaro

Associate Professor

Francesco Masulli

Associate Professor

Luca Oneto

Associate Professor

Luca Pedrelli

Post-doc Researcher

Rita Pucci

Post-Doc Researcher

Flavio Baronti

PhD Student

Francesco Crecchi

PhD Student

Daniele Di Sarli

PhD Student

Francesco Odierna

PhD Student

Alessandro Passaro

PhD Student

Daniela Rotelli

PhD Student

Antonio Bruno

Research Contractor

Franco Alberto Cardillo


Katuscia Cerbioni

Elena Palanca

Marco Righi




A computing toolkit for building efficient autonomous applications leveraging humanistic intelligence
Funder: EU H2020
Year: 2020-2022

Trustworthy AI Integrating Logic, Optimization and Reasoning
Funder: EU H2020
Year: 2020-2023

Decrease of cOgnitive decline, malnutRition and sedEntariness by elderly empowerment in lifestyle Management and social Inclusion
Funder: EU FP7
Year: 2013-2016

Robotics UBIquitous COgnitive Network
Funder: EU FP7
Year: 2011-2014



Brugada syndrome and Artificial Intelligence applications to Diagnosis
Funder: Regione Toscana
Year: 2020-2023

Allerta sismica precoce per infrastrutture sensibili (A. Micheli)
Funder: POR FSE 2014-2020
Year: 2018-2019

Learning non-Isomorph Structured Transductions for Image and Text fragments (D. Bacciu)
Funder: SIR-MIUR
Year: 2015-2018



Intel COVID-19 response grant
Collaborator: Intel
Year: 2020-2021

Artificial Intelligence for mobility monitoring and management
Collaborator: TAGES
Year: 2019-2019

Machine Learning models for industrial process of Big Data
Collaborator: ST Microelectronics
Year: 2015-2016


Machine Learning analysis of biological signals
Collaborator: Biobeats
Year: 2016-2016


Partner Institutions

CIML is part of the CLAIRE (Confederation of Laboratories for Artificial Intelligence Research in Europe) Research Network.

Highlighted Publications

D. Bacciu, F. Errica, A. Micheli, and M. Podda
A Gentle Introduction to Deep Learning for Graphs Neural Networks, 129, 203-221, 2020


C. Gallicchio and A. Micheli
Deep Reservoir Neural Networks for Trees Information Sciences, 480, 174-193, 2019


Software and Datasets

The CIML group developed and released software and data sets related to the Research Activities, including innovative ML models for structured data code and datasets for the application areas (related to the original paper publications).

See the “Read More” for a complete list.


Current CIML members have been teaching (since early 2000s)  courses related to Artificial Intelligence and Machine Learning for the BSc and MSc degrees of the University of Pisa.

Past Courses


Alessio Micheli
Tel: +39 050 2212798


Dipartimento di Informatica
Largo B. Pontecorvo, 3
56127 Pisa, Italy