v21: ICGI 2012 Proceedings

2026-06-10 · Source: Proceedings of Machine Learning Research · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Robotics & Autonomous Systems · Depth: Expert, short

Summary

The "Eleventh International Conference on Grammatical Inference" (ICGI 2012), held from September 5-8, 2012, at the University of Maryland, College Park, MD, USA, showcased a broad spectrum of research in the field. Papers presented advancements in learning various formal language models, including Probabilistic Deterministic Finite Automata (PDFA), Non-Deterministic Finite Automata, and different types of context-free and dependency grammars. Key contributions addressed methodological improvements such as active learning, bootstrapping from data streams, and leveraging contextual information for syntactic learning. The conference also explored the inference of complex structures like Probabilistic Subsequential Transducers and Partially Observable Markov Decision Processes (POMDPs). Furthermore, practical applications of grammatical inference were highlighted in diverse domains, including robotic planning, testing the Bounded Retransmission Protocol, and analyzing biological sequences for amyloidogenic regions.

Key takeaway

The Eleventh International Conference on Grammatical Inference (ICGI 2012) presents advancements in learning formal grammars and automata, covering techniques like active learning for probabilistic transducers and bootstrapping PDFAs. Contributions include inducing Partially Observable Markov Decision Processes (POMDPs) and scaling Non-Deterministic Finite Automata (NFA) induction on supercomputers. These methods offer practical applications in robotic planning, protocol verification, and bioinformatics, benefiting researchers in AI, ML, and formal language theory.

Topics

• Grammatical Inference
• Automata Learning
• Formal Language Theory
• Probabilistic Models
• Machine Learning Applications

Best for: AI Scientist, Research Scientist

Related on AIssential

• v217: Proceedings of ICGI 2023 — The 16th International Conference on Grammatical Inference (ICGI 2023), held from July 10-13, 2023, in Rabat, Morocco, presented a diverse program covering advancements in learning formal languages.
• v57: ICGI 2016 Proceedings — This volume, PMLR 57, compiles the proceedings of The 13th International Conference on Grammatical Inference, held in Delft, The Netherlands, from October 5-7, 2016.
• Synthesizing POMDP Policies: Sampling Meets Model-checking via Learning — Integrating sampling, automata learning, and model-checking enables formally guaranteed POMDP policy synthesis.
• Scaling Neuro-symbolic Problem Solving: Solver-Free Learning of Constraints and Objectives — A neuro-symbolic architecture with a probabilistic loss efficiently learns to solve NP-hard problems from natural inputs.
• A Full Numerical Rank Basis Selection Algorithm for Spectral Learning — The paper presents a new algorithm for full numerical rank basis selection in spectral learning.
• Textual Autograd Mechanics: Computation Graphs in Language Optimization — Textual Autograd Mechanics applies computation graphs to optimize language models by backpropagating text feedback.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Proceedings of Machine Learning Research.