Reducing Data Loading Bottleneck with Coarse Feature Vectors for Large Scale Learning.
Shingo TakamatsuCarlos GuestrinPublished in: BigMine (2014)
Keyphrases
- data sets
- prior knowledge
- raw data
- data collection
- database
- training data
- feature vectors
- supervised learning
- data points
- multiresolution
- learning process
- data structure
- databases
- knowledge discovery
- background knowledge
- synthetic data
- real world
- data processing
- data mining
- original data
- data analysis
- learned models
- noisy data
- data quality
- coarse to fine
- hidden variables
- human experts
- bayesian methods
- feature space
- data distribution
- knowledge acquisition
- data mining techniques
- image data
- learning algorithm
- data sources
- data model
- social networks
- xml documents
- bayesian networks