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...

This paper studies the problem of learning weighted automata from a finite sample of strings with real-valued labels. We consider several hypothesis classes of weighted automata defined in terms of three different measures: the norm of an automaton’s weights, the norm of the function computed by an automaton, and the norm of the corresponding Hankel matrix. We present new data-dependent general...

Introduction of micro-cellular networks offer a potential increase in capacity of cellular networks, but they create problems in management of the cellular networks. A solution to these problems is self-organizing channel assignment algorithm with distributed control. In this paper, ''le first introduce the model of cellular learning automata in which learning automata are used to adjust the st...

This paper presents libalf, a comprehensive, open-source library for learning formal languages. libalf covers various well-known learning techniques for finite automata (e.g. Angluin’s L∗, Biermann, RPNI etc.) as well as novel learning algorithms (such as for NFA and visibly one-counter automata). libalf is flexible and allows facilely interchanging learning algorithms and combining domain-spec...

We will demonstrate the impact of the integration of our most recently developed learning technology for inferring Register Automata into the LearnLib, our framework for active automata learning. This will not only illustrate the unique power of Register Automata, which allows one to faithfully model data independent systems, but also the ease of enhancing the LearnLib with new functionality.

This paper studies the problem of learning weighted automata from a finite labeled training sample. We consider several general families of weighted automata defined in terms of three different measures: the norm of an automaton’s weights, the norm of the function computed by an automaton, or the norm of the corresponding Hankel matrix. We present new data-dependent generalization guarantees fo...

anti-lock braking system (abs) is a nonlinear and time varying system including uncertainty, so it cannot be controlled by classic methods. intelligent methods such as fuzzy controller are used in this area extensively; however traditional fuzzy controller using simple type-1 fuzzy sets may not be robust enough to overcome uncertainties. for this reason an interval type-2 fuzzy controller is de...

Inductive learning is the method of learning from observations. Inductive learning has important applications over a wide range of area including pattern recognition, language acquisition, bio-informatics and intelligent agent design. Because of such diverse applicability, inductive learning methods including automata learning, grammar induction, hidden markov model learning and symbolic statis...

We describe an algorithm for learning simple timed automata, known as real-time automata. The transitions of real-time automata can have a temporal constraint on the time of occurrence of the current symbol relative to the previous symbol. The learning algorithm is similar to the redblue fringe state-merging algorithm for the problem of learning deterministic finite automata. In addition to sta...