This paper argues that the “kindergarten approach to learning” – characterized by a spiraling cycle of Imagine, Create, Play, Share, Reflect, and back to Imagine – is idea...
In large multiagent games, partial observability, coordination, and credit assignment persistently plague attempts to design good learning algorithms. We provide a simple and ef...
We explore algorithms for learning classification procedures that attempt to minimize the cost of misclassifying examples. First, we consider inductive learning of classification ...
Michael J. Pazzani, Christopher J. Merz, Patrick M...
Sublearning, a model for learning of subconcepts of a concept, is presented. Sublearning a class of total recursive functions informally means to learn all functions from that cla...
Statistical query (SQ) learning model of Kearns is a natural restriction of the PAC learning model in which a learning algorithm is allowed to obtain estimates of statistical prop...