Research Programs

LION - machine Learning and Intelligent OptimizatioN



The LION (machine Learning and Intelligent OptimizationN) laboratory fosters research and development in intelligent optimization and reactive search optimization (RSO) techniques for solving relevant problems arising in different application areas, including marketing automation and e-commerce, telecommunication networks, ICT, mobile services, big data, cost management, social networks, clustering and pattern recognition in bio-informatics.

We like the integration of different theoretical and practical tools in a creative environment that cuts across rigid borders between disciplines. This is the passion of LION activities. LION is building tools for the new prescriptive analytics wave.

We use data to build models and extract knowledge, we exploit knowledge to automate the discovery of improving solutions,  we connect insight to decisions and actions.

Research Areas

Big data, predictive analytics and optimization (prescriptive analytics)

Huge amounts of data are produced during business operations. The LIONlab develop methods and tools to mine this treasure and extract actionable insight. Applications are far-reaching, ranging from marketing and e-commerce to bioinformatics, healthcare and social networks. After models through "learning from data" methods are available, automated improvement motors (optimization) can be run to obtain better and better solutions.

Reactive Search and Intelligent Optimization  

Reactive Search advocates the integration of sub-symbolic machine learning techniques into local search heuristics for solving complex optimization problems. The word reactive hints at a ready response to events during the search through an internal online feedback loop for the self-tuning of critical parameters. Methodologies of interest for Reactive Search include machine learning and statistics, in particular reinforcement learning, active or query learning, neural networks, and meta-heuristics (although the boundary signalled by the "meta" prefix is not always clear).

Machine learning

The increasing availability of huge amounts of data in machine readable format from sources as diverse as databases of chemical compounds, DNA and protein sequences and structures, tagged bookmarks, digital libraries, images, web pages and blogs represent an unprecedented opportunity as well as a formidable challenge for machine learning systems. Such a complex body of information calls for the most recent advances in machine learning research in order to scale to large datasets, deal with complex structured data both in input and output, and jointly solve multiple related tasks, as well as learn models able to transfer knowledge among similar tasks. Models able to provide interpretable explanations for their decisions are especially appealing for the domain experts. Our research is mainly focused on kernel machine algorithms for structured data, multitask learning and statistical relational methods.

Machine learning and optimization for bioinformatics

Computational molecular biology is a hot research area and a continuous source of relevant and challenging problems for machine learning. Structural bioinformatics aims at predicting the three-dimensional structure of macromolecules such as proteins and RNA, given their sequence of residues or nucleotides. Given its intrinsic complexity, the problem has been addressed by tackling a number of related sub-tasks, such as secondary structure, contact map or disulphide bridge prediction. Being able to effectively solve such sub-tasks and combine their outputs into a reliable 3D structure predictor is one of the greatest challenges in bioinformatics. The activity of living cells involves a huge number of interactions between their components, which can be represented as regulatory, metabolic and interaction networks whose structure is mostly unknown. Machine learning techniques need to be able to combine heterogeneous and noisy sources of information from evolutionary, similarity and experimental data in order to contribute to discovering such relational structures.

Applications Areas

The wide applicability of reactive search and intelligent optimization techniques lead to various research projects in areas ranging from computer networks, to location-aware services, social networks, autonomic communications. A list of recent research projects follows.

  • Protein Function Prediction by Statistical Relational Learning (Google Faculty Research Award)
  • Apprendimento Statistico Relazionale e Reactive Search Optimization (PRIN grant)
  • Triton, Trentino Research and Innovation for Tunnel Monitoring 
  • Damasco, Data Acquisition and MAnagement in a Sensing and COmmunicating environment 
  • CASCADAS, Component-ware for Autonomic Situation-aware Communications, and Dynamically Adaptable Services 
  • BIONETS, BioNets - mating in the computer world AMICI, Amici del Parco 
  •, An Italian National Research Council Project on Grid Computing 
  • WILMA, Wireless Internet and Location Management Architecture 
  • E-NEXT, EU FP6 Network of Excellence on Internet protocols and services 
  • QuaSAR, "Qualita' e Controllabilita' dei Servizi di Comunicazione su Reti Eterogenee"
  • ADONIS, Algorithms for Dynamic Optical Networks based on Internet Solutions


Faculty Members

Roberto Battiti (Coord)Mauro Brunato

Further Information

Technical reports of Research Program
Published papers of Research Program