Sciweavers

610 search results - page 89 / 122
» Training a Selection Function for Extraction
Sort
View
TASLP
2010
105views more  TASLP 2010»
13 years 2 months ago
Non-Negative Tensor Factorization Applied to Music Genre Classification
Music genre classification techniques are typically applied to the data matrix whose columns are the feature vectors extracted from music recordings. In this paper, a feature vecto...
Emmanouil Benetos, Constantine Kotropoulos
ALT
2011
Springer
12 years 7 months ago
On the Expressive Power of Deep Architectures
Deep architectures are families of functions corresponding to deep circuits. Deep Learning algorithms are based on parametrizing such circuits and tuning their parameters so as to ...
Yoshua Bengio, Olivier Delalleau
ICDAR
2011
IEEE
12 years 7 months ago
Three Dimensional Rotation-Free Recognition of Characters
—In this paper, we propose a new method for three dimensional rotation-free recognition of characters in scene. In the proposed method, we employ the Modified Quadratic Discrimi...
Ryo Narita, Wataru Ohyama, Tetsushi Wakabayashi, F...
AAAI
2004
13 years 9 months ago
Text Classification by Labeling Words
Traditionally, text classifiers are built from labeled training examples. Labeling is usually done manually by human experts (or the users), which is a labor intensive and time co...
Bing Liu, Xiaoli Li, Wee Sun Lee, Philip S. Yu
WWW
2010
ACM
14 years 2 months ago
Entity relation discovery from web tables and links
The World-Wide Web consists not only of a huge number of unstructured texts, but also a vast amount of valuable structured data. Web tables [2] are a typical type of structured in...
Cindy Xide Lin, Bo Zhao, Tim Weninger, Jiawei Han,...