Classifying one billion data with a new distributed svm algorithm.
Thanh-Nghi DoFrançois PouletPublished in: RIVF (2006)
Keyphrases
- input data
- noisy data
- distributed data
- support vector machine svm
- data analysis
- machine learning
- learning algorithm
- computational complexity
- preprocessing
- expectation maximization
- data sets
- data transfer
- classification algorithm
- data sources
- detection algorithm
- database
- dynamic programming
- knowledge discovery
- worst case
- np hard
- data structure
- objective function
- data distribution
- similarity measure
- probability distribution
- data points
- search space
- segmentation algorithm
- genetic algorithm