Machine Learning Summer School (MLSS), Cambridge 2009

Gaussian Processes

author: Carl Edward Rasmussen, Max Planck Institute for Biological Cybernetics, Max Planck Institute
published: Nov. 2, 2009, recorded: September 2009, views: 5239

Slides

Slides
0:00	Solving Challenging Non-linear Regression Problems by Manipulating a Gaussian Distribution
4:38	The Prediction Problem (1)
6:18	The Prediction Problem (2)
6:34	The Prediction Problem (3)
7:26	The Prediction Problem (4)
8:50	Maximum likelihood, parametric model
10:42	Bayesian Inference, parametric model
11:02	Bayesian Inference, parametric model, cont.
13:58	Bayesian Inference, parametric model
14:22	The Gaussian Distribution
15:22	Conditionals and Marginals of a Gaussian
16:50	Conditionals and Marginals of a Gaussian
17:14	What is a Gaussian Process?
21:54	The marginalization property
23:38	Random functions from a Gaussian Process
26:58	Some values of the random function
28:10	Random functions from a Gaussian Process
28:50	Joint Generation
32:02	Sequential Generation
37:34	Function drawn at random from a Gaussian Process with Gaussian covariance
40:18	Maximum likelihood, parametric model
40:58	Bayesian Inference, parametric model
41:08	Bayesian Inference, parametric model, cont.
42:38	Non-parametric Gaussian process models
52:54	Prior and Posterior
56:14	Graphical model for Gaussian Process
58:22	Some interpretation
66:02	The marginal likelihood
67:34	Example: Fitting the length scale parameter
75:34	Why, in principle, does Bayesian Inference work? Occam’s Razor
77:10	Example: Fitting the length scale parameter
77:34	The marginal likelihood
79:10	An illustrative analogous example
84:55	Solving Challenging Non-linear Regression Problems by Manipulating a Gaussian Distribution

Report a problem or upload files

If you have found a problem with this lecture or would like to send us extra material, articles, exercises, etc., please use our ticket system to describe your request and upload the data.
Enter your e-mail into the 'Cc' field, and we will keep you updated with your request's status.

Lecture popularity: You need to login to cast your vote.