8:30-9:30am Introduction to Neural-Symbolic Learning and Reasoning - Luis Lamb
Introduction to neural-symbolic integration
- Thinking beyond deep learning
- Combining knowledge representation and learning from large-scale data
- Neural-Symbolic systems, learning and reasoning, knowledge extraction
9:30-10:00am Introduction to Fuzzy Logic - Luciano Serafini
10:30-11:30 Introduction to Logic Tensor Networks (LTNs) Luciano Serafini and Michael Spranger
- Combining First-order (fuzzy) logic and deep learning
- Examples of relational learning and reasoning in LTNs
- Maximizing satisfiability as machine learning
11:30-12:30am A practical introduction to learning and reasoning with LTNs - Michael Sparger and Luciano Serafini
Hands-on examples of learning and reasoning in LTN. Participants will be able to program LTNs.
- Supervised classification task with constraints
- Unsupervised learning (clustering) using LTNs
- Link prediction, i.e. detecting a link/relation R between two new data items
- Regression, i.e. predicting missing attribute values of a new data item on the basis of its semantic description
- Finding the level of truth of a given logical formula/new constraint, given data and possibly inconsistent knowledge/existing constraints.
- Garcez, Artur S. d'Avila, Krysia Broda, and Dov M. Gabbay. Neural-symbolic learning systems: foundations and applications. Springer, 2002.
- Diligenti, Michelangelo, Marco Gori, and Claudio Saccà. "Semantic-based regularization for learning and inference." Artificial Intelligence (2015).
- Bottou, Léon. "From machine learning to machine reasoning." Machine learning 94.2 (2014): 133-149.
- Serafini, Luciano, and Artur d'Avila Garcez. "Logic Tensor Networks: Deep Learning and Logical Reasoning from Data and Knowledge." 11th International Workshop on Neural-Symbolic Learning and Reasoning (NeSy16), The New School, New York, July 2016. arXiv:1606.04422.
- Donadello, Ivan, Luciano Serafini, and Artur d'Avila Garcez. "Logic Tensor Networks for Semantic Image Interpretation." In Proceedings of 26th International Joint Conference on Artificial Intelligence (IJCAI 2017). arXiv:1705.08968
- Gori, Marco. Machine Learning: A Constraint-Based Approach, MIT Press, Nov 2017.
Artur d’Avila Garcez (City, University of London - firstname.lastname@example.org): Garcez is Professor of Computer Science and Director of the Research Centre for Machine Learning at City, University of London. He holds a Ph.D. in Computer Science (2000) from Imperial College London. He co-authored two books: Neural-Symbolic Cognitive Reasoning (Springer, 2009) and Neural-Symbolic Learning Systems (Springer, 2002), and more than 150 peer-reviewed publications in Artificial Intelligence, Machine Learning, Neural Computing and Neural-Symbolic Computing. Garcez is president of the Neural-Symbolic Learning and Reasoning Association, editor of many journals and programme committee member for all the leading conferences in AI and neural computation, IJCAI, AAAI, NIPS, IJCNN. His research has received funding from the Nuffield foundation, CAPES, CNPq, the EU, the Daiwa Foundation, the Royal Society, Innovate UK, ESRC and EPSRC UK. He is fellow of the British Computer Society.
Marco Gori (University of Siena - email@example.com) Marco Gori received a Ph.D. degree in 1990 from Università di Bologna, Italy, while working partly as a visiting student at the School of Computer Science (McGill University, Montréal). In 1992, he became an associate professor of Computer Science at Università di Firenze and, in November 1995, he joined the Università di Siena, where he is currently full professor of computer science. His main interests are in machine learning, decision support systems, Web mining, and game playing. Dr Gori serves (has served) as an Associate Editor of a number of technical journals related to his areas of expertise and he has been the recipient of best paper awards and keynote speakers in a number of international conferences. He was the President of the Italian Association for Artificial Intelligence. He is a fellow of the ECCAI, the IEEE, and the IAPR.
Luis Lamb (UFRGS, firstname.lastname@example.org) Lamb is Professor and Vice Provost for Research (Pro-Rector for Research) at the Federal University of Rio Grande do Sul, Porto Alegre, Brazil. He holds both the Ph.D. in Computing Science from the Imperial College London (2000) and the Diploma of the Imperial College (D.I.C.) (2000). He has been Honorary Visiting Fellow at the Department of Computing, City University London. His research interests include: Logic in Computer Science and Artificial Intelligence, Machine Learning, and Neural Computation. Lamb has co-authored two research monographs: Neural-Symbolic Cognitive Reasoning (Springer 2009) and Compiled Labelled Deductive Systems (IoP 2004). He is an Editorial Board Member of the Cognitive Technologies Book Series (SpringerNature), and has been on the PC of IJCAI, AAAI, IJCNN and is Senior PC Member of IJCAI-ECAI-18. Lamb holds an Advanced Research Fellowship from the Brazilian National Research Council CNPq. He is a professional member of the ACM, ACM SIGACT, AAAI, AMS, ASL, IEEE, C&GCA, and the Brazilian Computer Society.
Luciano Serafini (Fondazione Bruno Kessler - email@example.com) Luciano Serafini is a 30 year experienced researcher in knowledge representation and reasoning, semantic web, and ontologies. Since 1989 he worked as a researcher at the Fondazione Bruno Kessler, leading the data and knowledge management research unit since 2007. Hi is the main inventor of the logic of context and multi-context systems and logic based ontology matching. In the last years he has enlarged his scientific interests by developing approaches for integrating logical reasoning and machine learning, and he is one of the main inventors of Logic Tensor Networks. He has taught several courses at University of Trento and Bolzano in database and knowledge representation and reasoning, served as a PC member in the main conferences in Artificial Intelligence, Ontologies, and Semantic Web. He has published more than 150 papers, and has an h-index of 41.
Michael Spranger (Sony Inc. - firstname.lastname@example.org): Spranger is a Researcher at the Fundamental Research Laboratory of Sony Computer Science Laboratories Inc. located in Tokyo, Japan. He holds a Ph.D. in Artificial Intelligence (2011) from Vrije Universiteit Brussels (Belgium). He authored more than 60 peer-reviewed publications in Artificial Intelligence, Machine Learning, Robotics and Natural Language Processing and holds patents on structured personal information processing. Spranger is the current chair of the IEEE task force on language and cognition. He served on the program committees of various conferences including IJCAI, Cogsci, Alife, IEEE ICDL-EPIROB and many workshops on language and robots (most recently GLU 2017 and Semdeep). His tutorial on language and robots recently won the prize of best tutorial at the summer school on Creativity and Evolution (CAES) 2016.