Learning and Automata (LearnAut) - LICS 2017 Workshop
June 19, Reykjavik (Iceland)
Website: https://learnaut.wordpress.com/

Grammatical Inference (GI) studies machine learning algorithms for classical recursive models of computations like automata and grammars. The expressive power of these models and the complexity of associated computational problems are a major research topic within theoretical computer science (TCS). This workshop aims at offering a favorable place for dialogue and at generating discussions between researchers from these two communities.

The workshop will have a particular emphasis on the recent successes due to collaborations between members with these two different backgrounds.

We invite submissions of recent works, possibly preliminary ones, related to the theme of the workshop. Similarly to how main machine learning conferences and workshops are organized, all accepted abstracts will be part of a poster session held during the workshop. Additionally, the Program Committee will select a subset of the abstracts for oral presentation. At least one author of each accepted abstract is expected to represent it at the workshop.

Topics of interest include (but are not limited to):
- Computational complexity of learning problems involving automata and formal languages.
- Algorithms and frameworks for learning models representing language classes inside and outside the Chomsky hierarchy, including tree and graph grammars.
- Learning problems involving models with additional structure, including numeric weights, inputs/outputs such as transducers, register automata, timed automata, Markov reward and decision processes, and semi-hidden Markov models.
- Relations between automata and recurrent neural networks.
- Active learning of finite state machines and formal languages.
- Methods for estimating probability distributions over strings, trees, graphs, or any data used as input for symbolic models.
- Applications of learning to formal verification and (statistical) model checking.
- Logical aspects of learning and grammatical inference.
- Theoretical studies of learnable classes of languages/representations.
- Metrics and other error measures between automata or formal languages.

The workshop will not have formal proceedings, but authors of accepted abstracts can choose to have their work published on the workshop webpage. Depending on the success of LearnAut, a special issue in a computer science journal may be edited, to which participants will be strongly encouraged to submit.

** Invited speakers **

Kim G. Larsen (Aalborg)
Mehryar Mohri (NYU & Google)
Alexandra Silva (UCL) [TBC]

** Submission instructions **

Submissions in the form of extended abstracts must be at most 4 pages long (plus at most two for bibliography and possible appendixes) and adhere to the IEEE Proceedings 2-column 10pt format used by LICS; LaTeX style files are available at http://www.ctan.org/tex-archive/macros/latex/contrib/IEEEtran/. We do accept submissions of work recently published or currently under review. Submissions do not need to be anonymized.

- Submission url: https://easychair.org/conferences/?conf=learnaut2017
- Submission deadline: April, 1st, 2017
- Notification of acceptance: mid-April, 2017
- LICS early registration deadline: TBA

** Program Committee **

Dana Angluin (Yale)
Jorge Castro (UPC)
François Denis (Aix-Marseille)
Jeff Heinz (Delaware)
Colin de la Higuera (Nantes)
Falk Howar (TU Clausthal)
José Oncina (Alicante)
Prakash Panangaden (McGill)
Ariadna Quattoni (Xerox)
Bernhard Steffen (TU Dortmund)
Sicco Verwer (TU Delft)
James Worrell (Oxford)

** Organizers **

Borja Balle (Lancaster)
Leonor Becerra-Bonache (Jean Monnet)
Remi Eyraud (Aix-Marseille)