Learning Probabilistic Finite Automata
نویسندگان
چکیده
Stochastic deterministic finite automata have been introduced and are used in a variety of settings. We report here a number of results concerning the learnability of these finite state machines. In the setting of identification in the limit with probability one, we prove that stochastic deterministic finite automata cannot be identified from only a polynomial quantity of data. If concerned with approximation results, they become Pac-learnable if the L∞ norm is used. We also investigate queries that are sufficient for the class to be learnable. keywords: Probabilistic grammar induction, query based learning, complexity results ? This work was supported in part by the IST Programme of the European Community, under the Pascal Network of Excellence, IST-2002-506778. This publication only reflects the authors’ views. Probabilistic finite automata cannot be learned 1
منابع مشابه
Probabilistic Deterministic Infinite Automata
We propose a novel Bayesian nonparametric approach to learning with probabilistic deterministic finite automata (PDFA). We define a PDFA with an infinite number of states (probabilistic deterministic infinite automata, or PDIA) and show how to average over its connectivity structure and state-specific emission distributions. Given a finite training sequence, posterior inference in the PDIA can ...
متن کاملLearning and Model-Checking Networks of I/O Automata
We introduce a new statistical relational learning (SRL) approach in which models for structured data, especially network data, are constructed as networks of communicating finite probabilistic automata. Leveraging existing automata learning methods from the area of grammatical inference, we can learn generic models for network entities in the form of automata templates. As is characteristic fo...
متن کاملLearning Probabilistic Residual Finite State Automata
We introduce a new class of probabilistic automata: Probabilistic Residual Finite State Automata. We show that this class can be characterized by a simple intrinsic property of the stochastic languages they generate (the set of residual languages is finitely generated) and that it admits canonical minimal forms. We prove that there are more languages generated by PRFA than by Probabilistic Dete...
متن کاملA Link Prediction Method Based on Learning Automata in Social Networks
Nowadays, online social networks are considered as one of the most important emerging phenomena of human societies. In these networks, prediction of link by relying on the knowledge existing of the interaction between network actors provides an estimation of the probability of creation of a new relationship in future. A wide range of applications can be found for link prediction such as electro...
متن کاملSpectral Learning from a Single Trajectory under Finite-State Policies
We present spectral methods of moments for learning sequential models from a single trajectory, in stark contrast with the classical literature that assumes the availability of multiple i.i.d. trajectories. Our approach leverages an efficient SVD-based learning algorithm for weighted automata and provides the first rigorous analysis for learning many important models using dependent data. We st...
متن کامل