On a Combinatorial Problem Arising in Machine Teaching

no code implementations • 7 Feb 2024 • Brigt Håvardstun, Jan Kratochvíl, Joakim Sunde, Jan Arne Telle

We study a model of machine teaching where the teacher mapping is constructed from a size function on both concepts and examples.

LEMMA

When Redundancy Matters: Machine Teaching of Representations

no code implementations • 23 Jan 2024 • Cèsar Ferri, Dario Garigliotti, Brigt Arve Toppe Håvardstun, Josè Hernández-Orallo, Jan Arne Telle

In traditional machine teaching, a teacher wants to teach a concept to a learner, by means of a finite set of examples, the witness set.

MAP- and MLE-Based Teaching

no code implementations • 11 Jul 2023 • Hans Ulrich Simon, Jan Arne Telle

an MLE-learner) if it thinks of a collection S of observations as a random sample and returns the concept with the maximum a-posteriori probability (resp.

Finite Biased Teaching with Infinite Concept Classes

no code implementations • 19 Apr 2018 • Jose Hernandez-Orallo, Jan Arne Telle

We investigate the teaching of infinite concept classes through the effect of the learning bias (which is used by the learner to prefer some concepts over others and by the teacher to devise the teaching examples) and the sampling bias (which determines how the concepts are sampled from the class).

Solving MaxSAT and #SAT on structured CNF formulas

no code implementations • 26 Feb 2014 • Sigve Hortemo Sæther, Jan Arne Telle, Martin Vatshelle

Let the ps-value of the formula be the number of precisely satisfiable sets of clauses.