Sciweavers

4660 search results - page 235 / 932
» Learning from imperfect data
Sort
View
INTERSPEECH
2010
14 years 12 months ago
A classifier-based target cost for unit selection speech synthesis trained on perceptual data
Our goal is to automatically learn a perceptually-optimal target cost function for a unit selection speech synthesiser. The approach we take here is to train a classifier on human...
Volker Strom, Simon King
ICML
2005
IEEE
16 years 5 months ago
Learning to rank using gradient descent
We investigate using gradient descent methods for learning ranking functions; we propose a simple probabilistic cost function, and we introduce RankNet, an implementation of these...
Christopher J. C. Burges, Tal Shaked, Erin Renshaw...
118
Voted
WMTE
2006
IEEE
15 years 11 months ago
JAMIOLAS: Supporting Japanese Mimicry and Onomatopoeia Learning with Sensors
  This  paper  proposes  a  computer  supported  ubiquitous  learning  environment  for  language  learning.  Especially,  this  paper  describes  context­  awar...
Hiroaki Ogata, Chengjiu Yin, Yoneo Yano
JMLR
2006
97views more  JMLR 2006»
15 years 5 months ago
Learning Coordinate Covariances via Gradients
We introduce an algorithm that learns gradients from samples in the supervised learning framework. An error analysis is given for the convergence of the gradient estimated by the ...
Sayan Mukherjee, Ding-Xuan Zhou
UM
2007
Springer
15 years 11 months ago
Evaluating a Simulated Student Using Real Students Data for Training and Testing
: SimStudent is a machine-learning agent that learns cognitive skills by demonstration. It was originally developed as a building block of the Cognitive Tutor Authoring Tools (CTAT...
Noboru Matsuda, William W. Cohen, Jonathan Sewall,...