We propose a method to learn heterogeneous models of object classes for visual recognition. The training images contain a preponderance of clutter and learning is unsupervised. Ou...
Existing definitions of the relativizations of NC1 , L and NL do not preserve the inclusions NC1 ⊆ L, NL ⊆ AC1 . We start by giving the first definitions that preserve them....
Abstract. We present a unified and complete account of maximum entropy distribution estimation subject to constraints represented by convex potential functions or, alternatively, b...
Given a set S of elements in a directed network that are initially faulty, an element becomes (functionally) faulty if all its in-neighbors or all its outneighbors are (functional...
— Kernel mapping is one of the most used approaches to intrinsically derive nonlinear classifiers. The idea is to use a kernel function which maps the original nonlinearly separ...