Speeding-up Document Scoring with Tree Ensembles using CPU SIMD Extensions.
Claudio LuccheseFranco Maria NardiniSalvatore OrlandoRaffaele PeregoNicola TonellottoRossano VenturiniPublished in: IIR (2016)
Keyphrases
- tree ensembles
- random forests
- document images
- information retrieval systems
- massively parallel
- document collections
- retrieval systems
- parallel algorithm
- neural network
- parallel implementation
- single instruction multiple data
- information retrieval
- parallel processing
- data mining
- learning algorithm
- feature selection