On Rfa Learnability of Boolean Functions

Learning with Limited Visibility

This paper surveys recent studies of learning problems in which the learner faces restrictions on the amount of information he can extract from each example he encounters. Our main framework for the analysis of such scenarios is the RFA (Restricted Focus of Attention) model. While being a natural reenement of the PAC learning model, some of the fundamental PAC-learning results and techniques fa...

Learnability and Characterization Results for Classes of Boolean Functions

Learnability of Some Eecient Representations of Boolean Functions

This thesis studies the learnability of several representation classes of Boolean functions: a restriction on k-term DNF, ordered binary decision diagrams and monotone term decision lists. We also show that some operations on these representation classes can be done in polynomial time. This fact is one of the motivations of the study (and use) of those classes.

Evolvability need not imply learnability

We show that Boolean functions expressible as monotone disjunctive normal forms are PAC-evolvable under a uniform distribution on the Boolean cube if the hypothesis size is allowed to remain fixed. We further show that this result is insufficient to prove the PAC-learnability of monotone Boolean functions, thereby demonstrating a counter-example to a recent claim to the contrary. We further dis...

Learning Boolean Functions

2 Probabilistic modelling of learning 4 2.1 A probabilistic model . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4 2.2 Definitions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.3 A learnability result for Boolean classes . . . . . . . . . . . . . . . . . . . . 6 2.4 Learning monomials . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 8 2.5 Di...