We prove that it is NP-hard to properly PAC learn decision trees with queries, resolving a longstanding open problem in learning theory (Bshouty 1993; Guijarro–Lavín–Raghavan 1999; Mehta–Raghavan 2002 ...

Decision trees are some kinds of learning structures which are used to provide approximations on the accurate solutions for new instances using learning data classifications. The core part in a ...

Studying a decision in archerfish reveals an impressive potential of learning capacities and cognitive aspects that are unexpected for decisions made at reflex speed.