Sciweavers

1136 search results - page 98 / 228
» Learning with Weighted Transducers
Sort
View
AI
1998
Springer
13 years 9 months ago
Worst-Case Analysis of the Perceptron and Exponentiated Update Algorithms
The absolute loss is the absolute difference between the desired and predicted outcome. This paper demonstrates worst-case upper bounds on the absolute loss for the Perceptron le...
Tom Bylander
ML
2010
ACM
141views Machine Learning» more  ML 2010»
13 years 7 months ago
Relational retrieval using a combination of path-constrained random walks
Scientific literature with rich metadata can be represented as a labeled directed graph. This graph representation enables a number of scientific tasks such as ad hoc retrieval o...
Ni Lao, William W. Cohen
CVPR
2008
IEEE
14 years 11 months ago
Interactive image segmentation via minimization of quadratic energies on directed graphs
We propose a scheme to introduce directionality in the Random Walker algorithm for image segmentation. In particular, we extend the optimization framework of this algorithm to com...
Dheeraj Singaraju, Leo Grady, René Vidal
ICML
2009
IEEE
14 years 10 months ago
Factored conditional restricted Boltzmann Machines for modeling motion style
The Conditional Restricted Boltzmann Machine (CRBM) is a recently proposed model for time series that has a rich, distributed hidden state and permits simple, exact inference. We ...
Graham W. Taylor, Geoffrey E. Hinton
JDWM
2007
122views more  JDWM 2007»
13 years 9 months ago
A Hyper-Heuristic for Descriptive Rule Induction
Rule induction from examples is a machine learning technique that finds rules of the form condition → class, where condition and class are logic expressions of the form variable...
Tho Hoan Pham, Tu Bao Ho