We construct a framework which allows an algorithm to turn the distributions produced by some boosting algorithms into polynomially smooth distributions (w.r.t. the PAC oracle...
Exploding amounts of multimedia data increasingly require automatic indexing and classification, e.g. training classifiers to produce high-level features, or semantic concepts, ch...
Wei Jiang, Eric Zavesky, Shih-Fu Chang, Alexander ...
Autonomous mobile robots need to adapt their behavior to the terrain over which they drive, and to predict the traversability of the terrain so that they can effectively plan thei...
Michael Shneier, Tommy Chang, Tsai Hong, William P...
Tuning compiler optimizations for rapidly evolving hardware makes porting and extending an optimizing compiler for each new platform extremely challenging. Iterative optimization i...
Grigori Fursin, Yuriy Kashnikov, Abdul Wahid Memon...
Active learning may hold the key for solving the data scarcity problem in supervised learning, i.e., the lack of labeled data. Indeed, labeling data is a costly process, yet an ac...