Expandable process networks to efficiently specify and explore task, data, and pipeline parallelism.
Lars SchorHoeseok YangIuliana BacivarovLothar ThielePublished in: CASES (2013)
Keyphrases
- data sets
- data collection
- data analysis
- training data
- network structure
- experimental data
- knowledge discovery
- redundant data
- raw data
- computer systems
- data processing
- data points
- historical data
- spatial data
- data distribution
- data sources
- high quality
- data acquisition
- database
- multiple types
- data quality
- data objects
- original data
- probability distribution
- missing data
- statistical analysis
- cloud computing
- distributed systems