Sciweavers

1748 search results - page 185 / 350
» Acceleration of the EM algorithm
Sort
View
133
Voted
CEC
2010
IEEE
15 years 4 months ago
Evolving natural language grammars without supervision
Unsupervised grammar induction is one of the most difficult works of language processing. Its goal is to extract a grammar representing the language structure using texts without a...
Lourdes Araujo, Jesus Santamaria
FCSC
2007
159views more  FCSC 2007»
15 years 3 months ago
Ranking with uncertain labels and its applications
1 The techniques for image analysis and classi cation generally consider the image sample labels xed and without uncertainties. The rank regression problem is studied in this pape...
Shuicheng Yan, Huan Wang, Jianzhuang Liu, Xiaoou T...
COLING
2010
14 years 10 months ago
A comparison of unsupervised methods for Part-of-Speech Tagging in Chinese
We conduct a series of Part-of-Speech (POS) Tagging experiments using Expectation Maximization (EM), Variational Bayes (VB) and Gibbs Sampling (GS) against the Chinese Penn Treeba...
Alex Cheng, Fei Xia, Jianfeng Gao
121
Voted
FOCI
2007
IEEE
15 years 9 months ago
Opposite Transfer Functions and Backpropagation Through Time
— Backpropagation through time is a very popular discrete-time recurrent neural network training algorithm. However, the computational time associated with the learning process t...
Mario Ventresca, Hamid R. Tizhoosh
121
Voted
ROBOCUP
2007
Springer
102views Robotics» more  ROBOCUP 2007»
15 years 9 months ago
Heuristic Reinforcement Learning Applied to RoboCup Simulation Agents
This paper describes the design and implementation of robotic agents for the RoboCup Simulation 2D category that learns using a recently proposed Heuristic Reinforcement Learning a...
Luiz A. Celiberto, Carlos H. C. Ribeiro, Anna Hele...