AbstractWe introduce a new class of nondeterministic semiautomata: A nondeterministic semiautomaton S is predictable if there exists k≥0 such that, if S knows the current input a and the next k inputs, the transition under a can be made deterministically. Nondeterminism may occur only when the length of the unread input is ≤k. We develop a theory of predictable semiautomata. We show that, if a semiautomaton with n states is k-predictable, but not (k−1)-predictable, then k≤(n2−n)/2, and this bound can be reached for a suitable input alphabet. We characterize k-predictable semiautomata, and introduce the predictor semiautomaton, based on a look-ahead semiautomaton. The predictor is essentially deterministic and simulates a nondeterministic se...
AbstractThis paper investigates the concept of randomness within a complexity theoretic framework. W...
This paper studies sequence prediction based on the monotone Kolmogorov complexity Km = -log m, i.e....
We study the properties of the Minimum Description Length principle for sequence prediction, conside...
Abstract. A nondeterministic semiautomaton S is predictable if there exists k ≥ 0 such that, if S kn...
AbstractWe introduce a new class of nondeterministic semiautomata: A nondeterministic semiautomaton ...
Abstract. It has been shown recently that deterministic semiautomata can be represented by canonical...
AbstractIt has been shown recently that deterministic semiautomata can be represented by canonical w...
AbstractWe investigate a model of polynomial-time concept prediction which is a relaxation of the di...
AbstractGiven a set X of sequences over a finite alphabet, we investigate the following three quanti...
Solomonoff's central result on induction is that the prediction of a universal semimeasure M converg...
AbstractIt is well known that allowing nondeterminism in a finite automaton can produce in the most ...
Abstract. We address the problem of predicting events ’ occurrences in partially observable timed sy...
The problem of predicting a sequence x1 , x2 , .... where each xi belongs to a finite alphabet...
Abstract. Choices made by nondeterministic word automata depend on both the past (the prefix of the ...
We show that any càdlàg predictable process of finite variation is an a.s. limit of elementary predi...
AbstractThis paper investigates the concept of randomness within a complexity theoretic framework. W...
This paper studies sequence prediction based on the monotone Kolmogorov complexity Km = -log m, i.e....
We study the properties of the Minimum Description Length principle for sequence prediction, conside...
Abstract. A nondeterministic semiautomaton S is predictable if there exists k ≥ 0 such that, if S kn...
AbstractWe introduce a new class of nondeterministic semiautomata: A nondeterministic semiautomaton ...
Abstract. It has been shown recently that deterministic semiautomata can be represented by canonical...
AbstractIt has been shown recently that deterministic semiautomata can be represented by canonical w...
AbstractWe investigate a model of polynomial-time concept prediction which is a relaxation of the di...
AbstractGiven a set X of sequences over a finite alphabet, we investigate the following three quanti...
Solomonoff's central result on induction is that the prediction of a universal semimeasure M converg...
AbstractIt is well known that allowing nondeterminism in a finite automaton can produce in the most ...
Abstract. We address the problem of predicting events ’ occurrences in partially observable timed sy...
The problem of predicting a sequence x1 , x2 , .... where each xi belongs to a finite alphabet...
Abstract. Choices made by nondeterministic word automata depend on both the past (the prefix of the ...
We show that any càdlàg predictable process of finite variation is an a.s. limit of elementary predi...
AbstractThis paper investigates the concept of randomness within a complexity theoretic framework. W...
This paper studies sequence prediction based on the monotone Kolmogorov complexity Km = -log m, i.e....
We study the properties of the Minimum Description Length principle for sequence prediction, conside...