Overcomplete sparsifying transform learning algorithm using a constrained least squares approach.
Ender Mete EksiogluOzden BayirPublished in: ICASSP (2014)
Keyphrases
- constrained least squares
- learning algorithm
- sparse representation
- regularized least squares
- basis vectors
- negative matrix factorization
- regularization parameter
- active learning
- linear combination
- machine learning
- natural images
- reinforcement learning
- training data
- sparse coding
- supervised learning
- learning problems
- nonnegative matrix factorization
- image classification
- basis functions
- least squares
- decision trees
- feature selection