16 search results - page 1 / 4 » Relative Loss Bounds and Polynomial-Time Predictions for the... |
ALT
2004
Springer
14 years 1 months ago
2004
Springer
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...
COLT
1993
Springer
13 years 9 months ago
1993
Springer
In this paper we demonstrate how weighted majority voting with multiplicative weight updating can be applied to obtain robust algorithms for learning binary relations. We first pre...
NIPS
1997
13 years 6 months ago
1997
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...
AAAI
1997
13 years 6 months ago
1997
The absolute loss is the absolute difference between the desired and predicted outcome. I demonstrateworst-case upper bounds on the absolute loss for the perceptron algorithm and ...
ALT
1999
Springer
13 years 9 months ago
1999
Springer
We are concerned with the problem of sequential prediction using a givenhypothesis class of continuously-manyprediction strategies. An e ectiveperformance measure is the minimax re...