The present work determines the exact nature of linear time computable notions which characterise automatic functions (those whose graphs are recognised by a finite automaton). The paper also determines which type of linear time notions permit full learnability for learning in the limit of automatic classes (families of languages which are uniformly recognised by a finite automaton). In particu...

A resurgent interest for grammatical inference aka automaton learning has emerged in several intriguing areas of computer sciences such as machine learning, software engineering, robotics and internet things. An algorithm commonly uses queries to learn the regular grammar a Deterministic Finite Automaton (DFA). These are posed Minimum Adequate Teacher (MAT) by learner (Learning Algorithm). The ...

We consider the problem of learning in dynamical systems with hidden state. This problem is deemed challenging due to the fact that the state is not completely visible to an outside observer. We explore a candidate algorithm, which we call the Merge-Split algorithm, for learning deterministic automata with observations. This is based on the work of Gavalda et al(2006) which approximates a given...

Abstract—This paper studies learning algorithm of the digital spike maps. The map is equivalent to a simple one-dimensional cellular automaton and can generate various digital spike-trains. In order to approximate a class of spike-trains, we present a learning algorithm with selforganizing function. Performing a basic numerical experiment, we have clarified that the map can learn a typical clas...

Abstract We show that the finite sequentiality problem is decidable for finitely ambiguous max-plus tree automata. A automaton a weighted over semiring. called if number of accepting runs on every bounded by global constant. The asks whether given automaton, there exist many deterministic automata whose pointwise maximum equivalent to automaton.

we prove that if $m$ is a monoid and $a$ a finite set with more than one element‎, ‎then the residual finiteness of $m$ is equivalent to that of the monoid consisting of all cellular automata over $m$ with alphabet $a$‎.

A framework for task assignment in heterogeneous computing systems is presented in this work. The framework is based on a learning automata model. The proposed model can be used for dynamic task assignment and scheduling and can adapt itself to changes in the hardware or network environment. The important feature of the scheme is that it can work on multiple cost criteria, optimizing each crite...

This work describes an approach for inferring De-terministic Context-free (DCF) Grammars in a Connectionist paradigm using a Recurrent Neu-ral Network Pushdown Automaton (NNPDA). The NNPDA consists of a recurrent neural network connected to an external stack memory through a common error function. We show that the NNPDA is able to learn the dynamics of an underlying push-down automaton from exa...