A Machine Learning-Based Approach for Selecting SpMV Kernels and Matrix Storage Formats.
Hang CuiShoichi HirasawaHiroaki KobayashiHiroyuki TakizawaPublished in: IEICE Trans. Inf. Syst. (2018)
Keyphrases
- machine learning
- kernel methods
- positive definite
- positive semidefinite
- kernel matrices
- linear combination
- matrix valued
- data storage
- active learning
- pattern recognition
- storage and retrieval
- kernel function
- multimedia
- selection algorithm
- machine learning methods
- knowledge acquisition
- dot product
- machine learning algorithms
- storage requirements
- positive semi definite
- inductive logic programming
- singular value decomposition
- learning systems
- data mining
- learning algorithm
- metadata
- computer science
- gram matrix
- artificial intelligence
- reinforcement learning
- data analysis
- covariance matrix
- support vector machine
- kernel learning
- text classification
- data management
- feature selection
- supervised learning
- decision trees
- valued data
- learning tasks
- multiple kernel learning
- kernel matrix
- model selection
- explanation based learning
- information extraction
- feature space
- low rank