This paper presents an active learning method that directly optimizes expected future error. This is in contrast to many other popular techniques that instead aim to reduce versio...
Information distillation techniques are used to analyze and interpret large volumes of speech and text archives in multiple languages and produce structured information of interes...
Active and cooperative learning methods represent a paradigm shift in the delivery of engineering education. These techniques recognize that the passive model of the typical colle...
— When an agent observes its environment, there are two important characteristics of the perceived information. One is the relevance of information and the other is redundancy. T...
Zhihui Luo, David A. Bell, Barry McCollum, Qingxia...
Scarcity and infeasibility of human supervision for large
scale multi-class classification problems necessitates active
learning. Unfortunately, existing active learning methods
...
Prateek Jain (University of Texas at Austin), Ashi...