2004 RecentAdvInBayesianInf

• (Bishop, 2004) ⇒ Christopher M. Bishop. (2004). “Recent Advances in Bayesian Inference Techniques.” Keynote Presentation at SIAM Conference on Data Mining.

Subject Headings: Bayesian Inference Algorithm, Variance Inference Algorithm, Relevance Vector Machine, Support Vector Machine.

Quotes

Relevance Vector Machine (Tipping, 1999)

• Bayesian alternative to support vector machine (SVM)
• Limitations of the SVM:

– two classes – large number of kernels (in spite of sparsity) – kernels must satisfy Mercer criterion – cross-validation to set parameters C (and ε) – decisions at outputs instead of probabilities

Properties – comparable error rates to SVM on new data – no cross-validation to set comlexity parameters – applicable to wide choice of basis function – multi-class classification – probabilistic outputs – dramatically fewer kernels (by an order of magnitude) – but, slower to train than SVM,

	Author	volume	Date Value	title	type	journal	titleUrl	doi	note	year
2004 RecentAdvInBayesianInf	Christopher M. Bishop			Recent Advances in Bayesian Inference Techniques			http://www.siam.org/meetings/sdm04/files/Keynote Bishop.pdf			2004