Titel:
Communication-Free Widened Learning of Bayesian Network Classifiers Using Hashed Fiedler Vectors
Beteiligte:
Sampson, Oliver R.
[Verfasser:in];
Borgelt, Christian
[Verfasser:in];
Berthold, Michael R.
[Verfasser:in]
Erschienen:
KOPS - The Institutional Repository of the University of Konstanz, 2018-10-05
Sprache:
Englisch
DOI:
https://doi.org/10.1007/978-3-030-01768-2_22
ISBN:
1665275650
Entstehung:
Anmerkungen:
Diese Datenquelle enthält auch Bestandsnachweise, die nicht zu einem Volltext führen.
Beschreibung:
Widening is a method where parallel resources are used to find better solutions from algorithms instead of merely trying to find the same solutions more quickly. To date, every example of Widening has used some from of communiucation between the parallel workers to maintain their distances from one another in the model space. For the first time, we present a communication-free, widened extension to a standard machine learning algorithm. By using Locality Sensitive Hashing on the Bayesian networks' Fiedler vectors, we demonstrate the ability to learn classifiers superior to those standard implementations and to those generated with a greedy heuristic alone ; published