Invited Talk: Learning with Intelligent Teacher: Similarity Control and Knowledge Transfer

Опубликовано 6 июня 2016, 23:05

In the talk, I will introduce a model of learning with Intelligent Teacher. In this model, Intelligent Teacher supplies (some) training examples (x i ,y i ),i=1,…,l,x i ∈X,y i ∈{−1,1} with additional (privileged) information) x ∗ i ∈X ∗ forming training triplets (x i ,x ∗ i ,y i ),i,…,l . Privileged information is available only for training examples and notavailablefortextexamples . Using privileged information it is required to find a better training processes (that use less examples or more accurate with the same number of examples) than the classical ones. In this lecture, I will present two additional mechanisms that exist in learning with Intelligent Teacher * The mechanism to control Student's concept of examples similarity and * The mechanism to transfer knowledge that can be obtained in space of privileged information to the desired space of decision rules. Privileged information exists for many inference problem and Student-Teacher interaction can be considered as the basic element of intelligent behavior.

research.microsoft.com