Learning on Fisher-Bingham Model Based on Normalizing Constant

Muhammad Ali, Michael Antolovich

Research output: Book chapter/Published conference paperConference paperpeer-review

Abstract

Our focus in this work is on the practical applicability of matrix variate Fisher-Bingham model for statistical inferences via Maximum Likelihood Estimation (MLE) technique using simple Bayesian classifier. The practicability of such parametric models on high dimensional data (e.g., via manifold valued data) remained a big hurdle since long i.e., mainly due to the difficult normalising constant naturally appear with them. We applied the method of Saddle Point Approximation (SPA) for calculating the corresponding normalising constant and then tested the validity and performance of the proposed algorithm on two datasets against the state of the art existing techniques and observed that the proposed technique is more suitable for recognition on Grassmann manifolds via a simple Bayesian classifier.
Original languageEnglish
Title of host publication2016 3rd International Conference on Soft Computing & Machine Intelligence (ISCMI)
Place of PublicationUnited States
PublisherIEEE, Institute of Electrical and Electronics Engineers
Pages33-37
Number of pages5
DOIs
Publication statusPublished - 23 Nov 2016
Event3rd International Conference on Soft Computing & Machine Intelligence : ISCMI 2016 - Flora Grand Hotel, Dubai, United Arab Emirates
Duration: 23 Nov 201625 Nov 2016
Conference number: 3rd
http://www.iscmi.us/ISCMI2016.html

Conference

Conference3rd International Conference on Soft Computing & Machine Intelligence
CountryUnited Arab Emirates
CityDubai
Period23/11/1625/11/16
Internet address

Fingerprint Dive into the research topics of 'Learning on Fisher-Bingham Model Based on Normalizing Constant'. Together they form a unique fingerprint.

Cite this