Proceedings in PMLR volume 217 (all the papers in one file here)

Monday, July 10

Faculty of Sciences, Mohammed V University in Rabat

13:00 Registration

13:45 Opening of the Conference

14:00 Distinguished lecture by Dana Angluin (Yale University, USA)
Learning of Regular Languages by Recurrent Neural Networks? (Mainly Questions)

15:00 Tutorial by Will Merrill (New York University, USA)
Formal languages and neural models for learning on sequences

18:00 Welcome cocktail

Tuesday, July 11

Hotel Farah Rabat

09:00 Invited talk

  • Weighted Finite Automata with Failure Transitions: Algorithms and Applications
    Cyril Allauzen (Google, New York) 

10:00 Coffee break

10:30 Session 1

  • Extending Distributional Learning from Positive Data and Membership Queries
    Makoto Kanazawa and Ryo Yoshinaka
  • Identification of Substitutable Context-Free Languages over Infinite Alphabets from Positive Data
    Yutaro Numaya, Diptarama Hendrian, Ryo Yoshinaka and Ayumi Shinohara
  • A Procedure for Inferring a Minimalist Lexicon from an SMT Model of a Language Acquisition Device
    Sagar Indurkhya
  • Learning Syntactic Monoids from Samples by extending known Algorithms for learning State Machines
    Simon Dieck and Sicco Verwer

12:30 Lunch

14:30 Session 2

  • String Extension Learning Despite Noisy Intrusions
    Katherine Wu and Jeffrey Heinz
  • fAST: regular expression inference from positive examples using Abstract Syntax Trees
    Maxime Raynal, Marc-Olivier Buob and Georges Quénot

15:30 Coffee break

16:00 Special session TAYSIR competition

  • TAYSIR Competition: Transformer+rnn: Algorithms to Yield Simple and Interpretable Representations
    Rémi Eyraud, Dakotah Lambert, Badr Tahri Joutei, Aidar Gaffarov, Mathias Cabanne, Jeffrey Heinz and Chihiro Shibata
  • Testing-based Black-box Extraction of Simple Models from RNNs and Transformers
    Edi Muškardin, Martin Tappler and Bernhard K. Aichernig
  • Results of Neural-Checker Toolbox in Taysir 2023 Competition
    Franz Mayr, Sergio Yovine, Matı́as Carrasco, Alejo Garat, Martı́n Iturbide, Juan da Silva and
    Federico Vilensky
  • A hybrid approach based HMM-Mixture Gaussian for estimating automata in Natural Language Processing
    Redouane Hakimi, Badreddine Benyacoub and Mohamed Ouzineb

18:00 Break for the day

Wednesday, July 12

Hotel Farah Rabat

09:00 Invited talk

  • A journey into the Generative AI and large language models: From NLP to BioInformatics
    Ahmed Elnaggar (Technische Universität München, Germany)

10:00 Coffee break

10:30 Session 3

  • Learning state machines from data streams: A generic strategy and an improved heuristic
    Robert Baumgartner and Sicco Verwer
  • Detecting Changes in Loop Behavior for Active Learning
    Bram Verboom, Simon Dieck and Sicco Verwer
  • Lower Bounds for Active Automata Learning
    Loes Kruger, Bharat Garhewal and Frits Vaandrager
  • Work in progress: Active Inference of Extended Finite State Models of Software Systems
    Roland Groz, Catherine Oriat, Germán Vega, Adenilso Simao, Michael Foster and Neil Walkinshaw

12:30 Lunch

14:30 ICGI business meeting

15:30  Social event and conference dinner

Thursday, July 13

Hotel Farah Rabat

09:00  Session 4

  • Benchmarking State-Merging Algorithms for Learning Regular Languages
    Adil Soubki and Jeffrey Heinz
  • Work in progress: Empirical and Theoretical Arguments for Using Properties of Letters for the Learning of Sequential Functions
    Magdalena Markowska and Jeffrey Heinz

10:00 Coffee break

10:30 Session 5

  • Formal and Empirical Studies of Counting Behaviour in ReLU RNNs
    Nadine El-Naggar, Andrew Ryzhikov, Laure Daviaud, Pranava Madhyastha and Tillman Weyde
  • Learning Transductions and Alignments with RNN Seq2seq Models
    Zhengxiang Wang
  • A Congruence-based Approach to Active Automata Learning from Neural Language Models
    Franz Mayr, Sergio Yovine, Matías Carrasco, Federico Pan and Federico Vilensky

12:00 Lunch

14:00 End of conference

Comments are closed.