PUMA
Istituto di Scienza e Tecnologie dell'Informazione     
Fagni T., Esuli A. SparkBOOST, an Apache spark-based boosting library. Technical report, 2016.
 
 
Abstract
(English)
SparkBOOST is a Java library built over Apache Spark that provides a distributed implementation of AdaBoost.MH and MP-Boost machine learning algorithms. These boosting algorithms are known to be very effective and robust to overfitting in many application domains, e.g. in natural language processing contexts. SparkBOOST offers to developers a fast way to scale these algorithms to large scale problems, where one needs to build classifiers from very large training datasets or simply needs to quickly classify huge stream of documents. The library can be integrated into custom programs by using a simple API. The SparkBOOST implementation also provides some command line tools to perform learning and classification on data sources available in LibSVM format.
Subject Boosting
Spark
Big data
D.2.2 SOFTWARE ENGINEERING. Design Tools and Techniques
D.2.11 Software Architectures
I.2.6 ARTIFICIAL INTELLIGENCE. Learning


Icona documento 1) Download Document PDF


Icona documento Open access Icona documento Restricted Icona documento Private

 


Per ulteriori informazioni, contattare: Librarian http://puma.isti.cnr.it

Valid HTML 4.0 Transitional