Sciweavers

1099 search results - page 66 / 220
» String Transformation Learning
Sort
View
TIT
2010
61views Education» more  TIT 2010»
14 years 8 months ago
Tunstall code, Khodak variations, and random walks
A variable-to-fixed length encoder partitions the source string into variable-length phrases that belong to a given and fixed dictionary. Tunstall, and independently Khodak, desig...
Michael Drmota, Yuriy A. Reznik, Wojciech Szpankow...
111
Voted
HCI
2007
15 years 3 months ago
Modeling Content and Expression of Learning Objects in Multimodal Learning Management Systems
The paper discusses the relation between accessibility and multimodality of learning objects. I present a framework, rooted in linguistics, that supports a clear distinction betwee...
Giorgio Brajnik
82
Voted
ICML
2005
IEEE
16 years 2 months ago
PAC-Bayes risk bounds for sample-compressed Gibbs classifiers
We extend the PAC-Bayes theorem to the sample-compression setting where each classifier is represented by two independent sources of information: a compression set which consists ...
François Laviolette, Mario Marchand
ICML
2003
IEEE
16 years 2 months ago
Marginalized Kernels Between Labeled Graphs
A new kernel function between two labeled graphs is presented. Feature vectors are defined as the counts of label paths produced by random walks on graphs. The kernel computation ...
Hisashi Kashima, Koji Tsuda, Akihiro Inokuchi
IDA
2001
Springer
15 years 6 months ago
Self-Supervised Chinese Word Segmentation
Abstract. We propose a new unsupervised training method for acquiring probability models that accurately segment Chinese character sequences into words. By constructing a core lexi...
Fuchun Peng, Dale Schuurmans