We study on-line generalized linear regression with multidimensional outputs, i.e., neural networks with multiple output nodes but no hidden nodes. We allow at the final layer tra...
We are concerned with the problem of sequential prediction using a givenhypothesis class of continuously-manyprediction strategies. An eectiveperformance measure is the minimax re...
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 present a family of margin based online learning algorithms for various prediction tasks. In particular we derive and analyze algorithms for binary and multiclass categorizatio...
We consider the problem of sequential decision making for random fields corrupted by noise. In this scenario, the decision maker observes a noisy version of the data, yet judged wi...