Sciweavers

667 search results - page 14 / 134
» Learning to Model Sequences Generated by Switching Distribut...
Sort
View
EMNLP
2007
13 years 11 months ago
Semi-Supervised Structured Output Learning Based on a Hybrid Generative and Discriminative Approach
This paper proposes a framework for semi-supervised structured output learning (SOL), specifically for sequence labeling, based on a hybrid generative and discriminative approach...
Jun Suzuki, Akinori Fujino, Hideki Isozaki
ICASSP
2010
IEEE
13 years 7 months ago
Efficient online learning with individual learning-rates for phoneme sequence recognition
We describe a fast and efficient online algorithm for phoneme sequence speech recognition. Our method is using a discriminative training to update the model parameters one utteran...
Koby Crammer
CIARP
2009
Springer
14 years 4 months ago
Learning Relational Grammars from Sequences of Actions
Many tasks can be described by sequences of actions that normally exhibit some form of structure and that can be represented by a grammar. This paper introduces FOSeq, an algorithm...
Blanca Vargas-Govea, Eduardo F. Morales
CONNECTION
2004
98views more  CONNECTION 2004»
13 years 9 months ago
Self-refreshing memory in artificial neural networks: learning temporal sequences without catastrophic forgetting
While humans forget gradually, highly distributed connectionist networks forget catastrophically: newly learned information often completely erases previously learned information. ...
Bernard Ans, Stephane Rousset, Robert M. French, S...
CVPR
2007
IEEE
14 years 11 months ago
Closed-Loop Tracking and Change Detection in Multi-Activity Sequences
We present a novel framework for tracking of a long sequence of human activities, including the time instances of change from one activity to the next, using a closed-loop, non-li...
Bi Song, Namrata Vaswani, Amit K. Roy Chowdhury