Sciweavers

687 search results - page 91 / 138
» Generalizing Dissimilarity Representations Using Feature Lin...
Sort
View
MICAI
2007
Springer
14 years 2 months ago
An EM Algorithm to Learn Sequences in the Wavelet Domain
The wavelet transform has been used for feature extraction in many applications of pattern recognition. However, in general the learning algorithms are not designed taking into acc...
Diego H. Milone, Leandro E. Di Persia
NIPS
2007
13 years 10 months ago
Discovering Weakly-Interacting Factors in a Complex Stochastic Process
Dynamic Bayesian networks are structured representations of stochastic processes. Despite their structure, exact inference in DBNs is generally intractable. One approach to approx...
Charlie Frogner, Avi Pfeffer
NN
2008
Springer
13 years 8 months ago
Multilayer in-place learning networks for modeling functional layers in the laminar cortex
Currently, there is a lack of general-purpose in-place learning networks that model feature layers in the cortex. By "general-purpose" we mean a general yet adaptive hig...
Juyang Weng, Tianyu Luwang, Hong Lu, Xiangyang Xue
MM
2009
ACM
233views Multimedia» more  MM 2009»
14 years 1 months ago
Enhancing semantic and geographic annotation of web images via logistic canonical correlation regression
Photo community sites such as Flickr and Picasa Web Album host a massive amount of personal photos with millions of new photos uploaded every month. These photos constitute an ove...
Liangliang Cao, Jie Yu, Jiebo Luo, Thomas S. Huang
POPL
2005
ACM
14 years 9 months ago
Associated types with class
Haskell's type classes allow ad-hoc overloading, or typeindexing, of functions. A natural generalisation is to allow type-indexing of data types as well. It turns out that th...
Manuel M. T. Chakravarty, Gabriele Keller, Simon L...