Sciweavers

16 search results - page 1 / 4
» Relative Loss Bounds and Polynomial-Time Predictions for the...
Sort
View
ALT
2004
Springer
14 years 3 months ago
Relative Loss Bounds and Polynomial-Time Predictions for the k-lms-net Algorithm
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...
Mark Herbster
COLT
1993
Springer
13 years 10 months ago
Learning Binary Relations Using Weighted Majority Voting
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...
Sally A. Goldman, Manfred K. Warmuth
NIPS
1997
13 years 7 months ago
Relative Loss Bounds for Multidimensional Regression Problems
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...
Jyrki Kivinen, Manfred K. Warmuth
AAAI
1997
13 years 7 months ago
Worst-Case Absolute Loss Bounds for Linear Learning Algorithms
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 ...
Tom Bylander
ALT
1999
Springer
13 years 10 months ago
Extended Stochastic Complexity and Minimax Relative Loss Analysis
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...
Kenji Yamanishi