Known algorithms for learning PDFA can only be shown to run in time polynomial in the so-called distinguishability μ of the target machine, besides the number of states and the usual accuracy and confidence parameters. ...

We study in this note the relationships between two usual models of learning via queries: the so-called exact and bounded learning models. One of our goals is to point out under which conditions the learning dimension ...

Markovian models with hidden state are widely-used formalisms for modeling sequential phenomena. Learnability of these models has been well studied when the sample is given in batch mode, and algorithms with PAC-like ...

We give some characterizations of the classes P super NP [0(log super k n)]. First, we show that these classes are equal to classes AC super k-1 (N P). Second, we prove that they are also equivalent to some classes defined ...

In this paper we extend the PAC learning algorithm due to Clark and Thollard for learning distributions generated by PDFA to automata whose transitions may take varying time lengths, governed by exponential distributions.

We review methods for inference of probability distributions generated by probabilistic automata and related models for sequence generation. We focus on methods that can be proved to learn in the inference in the limit ...

This paper introduces a framework for quantum exact learning via queries, the so-called quantum protocol. It is shown that usual protocols in the classical learning setting have quantum counterparts. A combinatorial notion, ...

In this post recession time it is important to measure the possibilities offered by a society in relation to investments. To do that, we consider an investment schema I= (R;R_1,...,R_n) where R is a lower bound on the ...

Nowadays interactions with the World Wide Web are ubiquitous. Users interact through a number of steps consisting of site calls and handling results that can be automatized as orchestrations. Orchestration results have ...

We prove that log n-decision lists - the class of decision lists such that all their terms have low Kolmogorov complexity - are learnable in the simple PAC learning model. The proof is based on a transformation from an ...