Procedures for collective inference make simultaneous statistical judgments about the same variables for a set of related data instances. For example, collective inference could b...
— Parallel algorithms are presented for modules of learning automata with the objective of improving their speed of convergence without compromising accuracy. A general procedure...
We start by showing that in an active learning setting, the Perceptron algorithm needs Ω( 1 ε2 ) labels to learn linear separators within generalization error ε. We then prese...
Sanjoy Dasgupta, Adam Tauman Kalai, Claire Montele...
Can we leverage learning techniques to build a fast nearest-neighbor (ANN) retrieval data structure? We present a general learning framework for the NN problem in which sample que...
The use of new technology must be combined with modern teaching practices to be effective. Collaborative learning is a general term employed for a variety of classroom practices d...