The present work initiates the study of the learnability of automatic indexable classes which are classes of regular languages of a certain form. Angluin’s tell-tale condition characterises when these classes are explanatorily learnable. Therefore, the more interesting question is when learnability holds for learners with complexity bounds, formulated in the automata-theoretic setting. The lear...

In order to systematize existing results, we propose to analyze the learnability of boolean functions computed by an algebraically defined model, programs over monoids. The expressiveness of the model, hence its learning complexity, depends on the algebraic structure of the chosen monoid. We identify three classes of monoids that can be identified, respectively, from Membership queries alone, E...

Objective. There are many smartphone-based applications (apps) for cardiopulmonary resuscitation (CPR) training. We investigated the conformity and the learnability/usability of these apps for CPR training and real-life supports. Methods. We conducted a mixed-method, sequential explanatory study to assess CPR training apps downloaded on two apps stores in South Korea. Apps were collected with i...

We apply a complexity theoretic notion of feasible learnability called "polynomial learnability" to the evaluation of grammatical formalisms for linguistic description. We show that a novel, nontrivial constraint on the degree of "locality" of grammars allows not only context free languages but also a rich class of mildly context sensitive languages to be polynomially learnable. We discuss poss...

This thesis examines so-called folding neural networks as a mechanism for machine learning. Folding networks form a generalization of partial recurrent neural networks such that they are able to deal with tree structured inputs instead of simple linear lists. In particular, they can handle classical formulas { they were proposed originally for this purpose. After a short explanation of the neur...

Probably Approximately Correct (i.e., PAC) learning is a core concept of sample complexity theory, and efficient PAC learnability often seen as natural counterpart to the class P in classical computational complexity. But while nascent theory parameterized has allowed us push beyond P-NP "dichotomy" identify exact boundaries tractability for numerous problems, there no analogue domain that coul...