914 search results - page 106 / 183 » Learning to Segment |
100
Voted
MM
2004
ACM
15 years 6 months ago
2004
ACM
This paper considers the problems of feature variation and concept uncertainty in typical learning-based video semantic classification schemes. We proposed a new online semantic c...
79
Voted
AAI
2008
15 years 29 days ago
2008
We present a novel hybrid technique for improving the predictive performance of an online Machine Learning system: Combining advantages from both memory based and concept based pr...
125
click to vote
INTERSPEECH
2010
14 years 7 months ago
2010
In this paper, we propose a novel boosted mixture learning (BML) framework for Gaussian mixture HMMs in speech recognition. BML is an incremental method to learn mixture models fo...
101
Voted
GECCO
2005
Springer
15 years 6 months ago
2005
Springer
This paper proposes a novel constructive learning algorithm for a competitive neural network. The proposed algorithm is developed by taking ideas from the immune system and demons...
122
click to vote
NLPRS
2001
Springer
15 years 5 months ago
2001
Springer
We describe a new tagging model where the states of a hidden Markov model (HMM) estimated by unsupervised learning are incorporated as the features in a maximum entropy model. Our...