Modal Symbolic Learning
-----------------------------------
          
ABSTRACT
-----------------------------------
Symbolic learning is the sub-field of machine learning that 
addresses the problem of learning symbolic properties from data. 
The main drawback with canonical symbolic learning models and 
algorithms (e.g., decision tree classifiers, rule-based classifiers) 
is that they are essentially standing on the shoulders of 
classical propositional logic, which is not always adequate when 
dealing with more-than-propositional, dimensional, and complex 
situations such as temporal, spatial, or textual data. 
In this talk, we show how to enhance the expressivity of 
propositional models by substituting propositional logic with 
more expressive formalisms based on modal logic, with the purpose 
of preserving the interesting properties of symbolic models (transparency 
and interpretability, among others), while increasing their 
performances and expressive power. 
We lay down a formal theory of modal symbolic learning, paving 
the way for a new research directions that explore the connection 
between modal, temporal, spatial logics and machine learning.
          
SPEAKER(S)
-----------------------------------
Guido Sciavicco holds a Bachelor, a Master, and a
PhD in Computer Science from the University of Udine (Italy). 
He has been working as junior and senior Post-Doc researcher 
at the University of Murcia (Spain), and as visiting assistant 
professor at the University for Information Science and 
Technology (Macedonia) as well as the Middle East Technical 
University (Cyprus). 
Now, he is Associate Professor at the University of Ferrara,
where he also is the director of the Applied Computational 
Logic and Artificial Intelligence Lab. 
Guido Sciavicco is co-author of more than 120 publications in 
many areas of logic and artificial intelligence, and he has 
directed several PhD thesis both in Spain and in Italy. 
He is also member of the Formal Verification, Logic, Automata, 
and Synthesis (OVERLAY) research group, member of the National 
Group of Scientific Computing (GNCS), and associate editor of 
the Journal of Computer Science, and of Expert Systems, both 
indexed in Scopus.
Guido Sciavicco h-index is 26 in Google Scholar, and 17 in Scopus.
          
Eduard is a PhD fellow, founded by the Italian Ministry of 
Universities and Research, in Mathematics at the Applied 
Computational Logic and Artificial Intelligence Lab., 
under the supervision of Guido Sciavicco. 
He obtained his Master's and Bachelor's degrees in Computer Science 
both cum laude from the University of Udine and University of 
Ferrara, Italy, respectively. 
Eduard has been awarded as being the best computer science 
student in his Master's degree for the academic year 2018/2019. 
He is co-author of more than 10 publications (h-index 4 in 
Google Scholar, and 3 in Scopus). He is also member of the Formal 
Verification, Logic, Automata, and Synthesis (OVERLAY) research group, 
member of the National Group of Scientific Computing (GNCS), 
member of the Artificial Intelligence in Romania community, 
deputy-coordinator of the Association of Doctoral Students and 
PhDs in Italy of Ferrara (ADI Ferrara), PhD students' representative 
in the Department of Mathematics and Computer Science at the 
University of Ferrara, and 35th PhD cycle students' representative 
in the Academic Board of the Department of Mathematical, Physical, 
and Computer Sciences at the University of Parma.