We study the convergence and the rate of convergence of a local manifold learning algorithm: LTSA [13]. The main technical tool is the perturbation analysis on the linear invarian...
We consider a two-layer network algorithm. The first layer consists of an uncountable number of linear units. Each linear unit is an LMS algorithm whose inputs are first “kerne...
We focus on the problem of efficient learning of dependency trees. Once grown, they can be used as a special case of a Bayesian network, for PDF approximation, and for many other u...
A learning problem might have several measures of complexity (e.g., norm and dimensionality) that affect the generalization error. What is the interaction between these complexiti...
We present a new type of multi-class learning algorithm called a linear-max algorithm. Linearmax algorithms learn with a special type of attribute called a sub-expert. A sub-exper...