Title :
Multi-task beta process sparse kernel machines
Author_Institution :
Sch. of Comput. & Math., Charles Sturt Univ., Bathurst, NSW, Australia
fDate :
July 31 2011-Aug. 5 2011
Abstract :
In this paper we propose a nonparametric extension to the sparse kernel machine using a beta process prior. The extended beta process sparse kernel machine (BPSKM) allows for a sparse model to be constructed from a set of training data. The recent research on beta process reveals elegant property of Bayesian conjugate prior which is utilized to derive a variational Bayes inference algorithm. The performance of the proposed algorithm has been investigated on both synthetic and real-life data sets.
Keywords :
Bayes methods; inference mechanisms; learning (artificial intelligence); multiprogramming; sparse matrices; Bayesian conjugate prior; multitask beta process sparse kernel machine; nonparametric extension; real-life data set; variational Bayes inference algorithm; Bayesian methods; Data models; Kernel; Machine learning; Sparse matrices; Training; Training data;
Conference_Titel :
Neural Networks (IJCNN), The 2011 International Joint Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4244-9635-8
DOI :
10.1109/IJCNN.2011.6033214
