Recent approaches to learning structured predictors often require approximate inference for tractability; yet its effects on the learned model are unclear. Meanwhile, most learnin...
Abstract. Classical learning algorithms from the fields of artificial neural networks and machine learning, typically, do not take any costs into account or allow only costs depe...
We prove strong noise-tolerance properties of a potential-based boosting algorithm, similar to MadaBoost (Domingo and Watanabe, 2000) and SmoothBoost (Servedio, 2003). Our analysi...
In this paper we report on techniques for automatically learning foveal sensing strategies for an active pan-tiltzoom camera. The approach uses reinforcement learning to discover ...
Andrew D. Bagdanov, Alberto Del Bimbo, Walter Nunz...
We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...