X-mHMM: An Efficient Algorithm for Training Mixtures of HMMs When the Number of Mixtures Is Unknown.
Zoltán SzamonekCsaba SzepesváriPublished in: ICDM (2005)
Keyphrases
- expectation maximization
- computational complexity
- experimental evaluation
- detection algorithm
- computationally efficient
- learning algorithm
- times faster
- space complexity
- optimal solution
- memory requirements
- k means
- computational cost
- optimization algorithm
- mixtures of gaussians
- training algorithm
- matching algorithm
- simulated annealing
- cost function
- preprocessing
- image segmentation
- particle swarm optimization
- high accuracy
- back propagation
- worst case
- training process
- objective function
- viterbi algorithm
- neural network