1. Relational Learning with Gaussian Processes By Wei Chu, Vikas Sindhwani, Zoubin Ghahramani, S.Sathiya Keerthi (Columbia, Chicago, Cambridge, Yahoo!) Presented by Nesreen Ahmed, Nguyen Cao, Sebastian Moreno, Philip Schatz
2.
3.
4.
5.
6.
7.
8. Relational Gaussian Processes 12/02/08 CS590M: Statistical Machine Learning - Fall 2008 where is a nxn matrix with four non-zero entries augmented from
17. 12/02/08 CS590M: Statistical Machine Learning - Fall 2008 30 Samples collected from a gaussian mixture with two components on the x-axis. Two labeled samples indicated by diamond and circle. K=3 Best value =0.4 based on approximate model evidence Results
18. 12/02/08 CS590M: Statistical Machine Learning - Fall 2008 Posterior Covariance matrix of RGP learnt from the data It captures the density information of unlabelled data Using the posterior covariance matrix learnt from the data as the new prior, supervised learning is carried out Curves represent predictive distribution for each class Results