Authors
Fabrizio Riguzzi
Dipartimento di Matematica e Informatica
Università di Ferrara
Abstract
The combination of logic and probability is very useful for modeling domains with complex and uncertain relationships among entities. Machine learning approaches based on such combinations have recently achieved important results, originating the fields of Statistical Relational Learning, Probabilistic Inductive Logic Programming and, more generally, Statistical Relational Artificial Intelligence.
The tutorial will concentrate on Probabilistic Logic Programming, a form of Probabilistic Programming that is receiving an increasing attention for its ability to combine powerful knowledge representation with Turing completeness.
This tutorial will introduce probabilistic logic programming and overview the main systems for learning models in these formalisms both in terms of parameters and of structure. The tutorial includes a significant hands-on experience with the systems ProbLog2 and cplint using the web applications https://dtai.cs.kuleuven.be/problog/ and http://cplint.eu that the attendants can access with their notebooks via wifi.
Speaker’s bio
Fabrizio Riguzzi is Associate Professor of Computer Science at the Department of Mathematics and Computer Science of the University of Ferrara. He was previously Assistant Professor at the same university. He got his Master and PhD in Computer Engineering from the University of Bologna.
Fabrizio Riguzzi is the Editor in Chief of Intelligenza Artificiale, the official journal of the Italian Association for Artificial Intelligence, and vice-president of the Association.
He is the author of more than 150 peer reviewed papers in the areas of Machine Learning, Inductive Logic Programming and Statistical Relational Learning.
His aim is to develop intelligent systems by combining in novel ways techniques from artificial intelligence, logic and statistics.
Outline
- Introduction
- Statistical Relational Learning
- Probabilistic Programming
- Logic Programming
- Probabilistic Logic Programming
- Sato’s distribution semantics
- Languages adopting the distribution semantics: Independent Choice Logic, PRISM, Logic Programs with Annotated Disjunctions, CP-logic, ProbLog
- Inference algorithms
- Exact inference by knowledge compilation
- Approximate inference by sampling
- ProbLog (hands on with https://dtai.cs.kuleuven.be/problog/)
- cplint (hands on with http://cplint.eu)
- Parameter learning
- Gradient descent approaches
- EM algorithm approaches
- LeProbLog
- ProbLog2 (hands on with https://dtai.cs.kuleuven.be/problog/)
- EMBLEM (hands on with http://cplint.eu})
- Structure learning
- Search strategies
- Stochastic search
- SLIPCOVER (hands on with http://cplint.eu)
- ProbFOIL
Relevant References
Book Foundations of Probabilistic Logic Programming, Fabrizio Riguzzi, River Publishers 2018
Fabrizio Riguzzi, Elena Bellodi, and Riccardo Zese. A history of probabilistic inductive logic programming. Frontiers in Robotics and AI, 1(6):1-5, 2014.