The nature of statistical learning theory
The nature of statistical learning theory
Phase transitions and the search problem
Artificial Intelligence - Special volume on frontiers in problem solving: phase transitions and complexity
Recent advances of grammatical inference
Theoretical Computer Science - Special issue on algorithmic learning theory
Phase Transitions in Relational Learning
Machine Learning
ICGI '98 Proceedings of the 4th International Colloquium on Grammatical Inference
What Is the Search Space of the Regular Inference?
ICGI '94 Proceedings of the Second International Colloquium on Grammatical Inference and Applications
Inductive Inference, DFAs, and Computational Complexity
AII '89 Proceedings of the International Workshop on Analogical and Inductive Inference
Relational learning as search in a critical region
The Journal of Machine Learning Research
Semantic types of some generic relation arguments: detection and evaluation
HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
A phase transition-based perspective on multiple instance kernels
ILP'07 Proceedings of the 17th international conference on Inductive logic programming
Hi-index | 0.00 |
It is now well-known that the feasibility of inductive learning is ruled by statistical properties linking the empirical risk minimization principle and the "capacity" of the hypothesis space. The discovery, a few years ago, of a phase transition phenomenon in inductive logic programming proves that other fundamental characteristics of the learning problems may similarly affect the very possibility of learning under very general conditions. Our work examines the case of grammatical inference. We show that while there is no phase transition when considering the whole hypothesis space, there is a much more severe "gap" phenomenon affecting the effective search space of standard grammatical induction algorithms for deterministic finite automata (DFA). Focusing on the search heuristics of the RPNI and RED-BLUE algorithms, we show that they overcome this problem to some extent, but that they are subject to overgeneralization. The paper last suggests some directions for new generalization operators, suited to this Phase Transition phenomenon.