Multi-view learning has become a hot topic during the past few years. In this paper, we first characterize the sample complexity of multi-view active learning. Under the expansion...
We introduce a computationally feasible, "constructive" active learning method for binary classification. The learning algorithm is initially formulated for separable cl...
Abstract. It is shown that high-order feedforward neural nets of constant depth with piecewisepolynomial activation functions and arbitrary real weights can be simulated for Boolea...
In this paper we present a novel method for parsing aerial images with a hierarchical and contextual model learned in a statistical framework. We learn hierarchies at the scene an...
Jake Porway, Kristy Wang, Benjamin Yao, Song Chun ...
We examine the relationship between the VCdimension and the number of parameters of a smoothly parametrized function class. We show that the VC-dimension of such a function class ...
Wee Sun Lee, Peter L. Bartlett, Robert C. Williams...