Training sparse MS-SVR with an expectation-maximization algorithm.
D. N. ZhengJ. X. WangY. N. ZhaoPublished in: Neurocomputing (2006)
Keyphrases
- expectation maximization
- em algorithm
- k means
- cost function
- dynamic programming
- training algorithm
- np hard
- matching algorithm
- detection algorithm
- recognition algorithm
- search space
- computational cost
- maximum likelihood
- training phase
- training process
- segmentation algorithm
- objective function
- support vector machine svm
- optimization algorithm
- worst case
- probabilistic model
- bayesian framework
- artificial neural networks
- optimal solution
- maximum likelihood estimation
- neural network