This article proposes an active basis model and a shared pursuit algorithm for learning deformable templates from image patches of various object categories. In our generative mod...
Ying Nian Wu, Zhangzhang Si, Chuck Fleming, Song C...
The focus of my thesis is on the development of a multi-method framework for the validation of formal models (domain model, user model, and teaching model) for adaptive work-integr...
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
We study the dynamics of a Hebbian ICA algorithm extracting a single non-Gaussian component from a high-dimensional Gaussian background. For both on-line and batch learning we fin...
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...