Range-Based ICA Using a Nonsmooth Quasi-Newton Optimizer for Electroencephalographic Source Localization in Focal Epilepsy.
S. Easter SelvanS. Thomas GeorgeR. BalakrishnanPublished in: Neural Comput. (2015)
Keyphrases
- quasi newton
- source localization
- superlinear convergence
- newton method
- eeg data
- independent component analysis
- eeg signals
- wireless sensor networks
- signal processing
- optimization methods
- convergence analysis
- optimization method
- face recognition
- step size
- linear equations
- variational inequalities
- optimization algorithm
- optimality conditions
- regularized least squares
- blind source separation
- brain computer interface
- machine learning
- linear svm
- quadratic programming
- neural network
- sound source
- nonnegative matrix factorization
- principal component analysis
- interior point methods
- global convergence
- hidden markov models
- optimization procedure
- convergence speed
- support vector
- feature extraction
- mean shift