NLP tasks are often domain specific, yet systems can learn behaviors across multiple domains. We develop a new multi-domain online learning framework based on parameter combinatio...
Active learning methods seek to reduce the number of labeled examples needed to train an effective classifier, and have natural appeal in spam filtering applications where trustwo...
Abstract. In this paper we study distributed online learning of locomotion gaits for modular robots. The learning is based on a stochastic approximation method, SPSA, which optimiz...
Detecting abnormal behaviors in crowd scenes is quite important for public security and has been paid more and more attentions. Most previous methods use offline trained model to p...
The idea of learning overcomplete dictionaries based on the paradigm of compressive sensing has found numerous applications, among which image denoising is considered one of the m...