Sciweavers

1343 search results - page 181 / 269
» Learning Weighted Automata
Sort
View
ICDAR
2011
IEEE
13 years 10 months ago
Objective Function Design for MCE-Based Combination of On-line and Off-line Character Recognizers for On-line Handwritten Japane
—This paper describes effective object function design for combining on-line and off-line character recognizers for on-line handwritten Japanese text recognition. We combine on-l...
Bilan Zhu, Jinfeng Gao, Masaki Nakagawa
ICPR
2004
IEEE
16 years 5 days ago
Fast Object and Pose Recognition Through Minimum Entropy Coding
We present a pattern recognizer to classify a variety of objects and their pose on a table from real world images. Learning of weights in a linear discriminant is based on estimat...
Günter Westphal, Rolf P. Würtz
AI
2009
Springer
15 years 5 months ago
Training Global Linear Models for Chinese Word Segmentation
This paper examines how one can obtain state of the art Chinese word segmentation using global linear models. We provide experimental comparisons that give a detailed road-map for ...
Dong Song, Anoop Sarkar
ISDA
2006
IEEE
15 years 5 months ago
Modular Neural Network Task Decomposition Via Entropic Clustering
The use of monolithic neural networks (such as a multilayer perceptron) has some drawbacks: e.g. slow learning, weight coupling, the black box effect. These can be alleviated by t...
Jorge M. Santos, Luís A. Alexandre, Joaquim...
CMMR
2004
Springer
118views Music» more  CMMR 2004»
15 years 4 months ago
Methods for Combining Statistical Models of Music
Abstract. The paper concerns the use of multiple viewpoint representation schemes for prediction with statistical models of monophonic music. We present an experimental comparison ...
Marcus Pearce, Darrell Conklin, Geraint A. Wiggins