International Conference on Machine Learning - Bonn 2005

How to Predict Sequences with Bayes, MDL, and Experts

author: Marcus Hutter, IDSIA

You might be experiencing some problems with Your Video player.

*Slides*
0:03	How to Predict Sequences with
1:39	Overview
7:40	Table of Contents
8:34	Philosophical Issues: Contents
8:42	Philosophical Issues: Abstract
8:48	On the Foundations of Machine Learning
9:54	Example 1: Probability of Sunrise Tomorrow
13:20	Example 2: Digits of a Computable Number
14:36	Example 3: Number Sequences
16:35	Occam's Razor to the Rescue
17:12	Foundations of Induction
18:03	Problem Setup
19:30	Dichotomies in Machine Learning
22:12	Sequential/online predictions
24:42	Bayesian Sequence Prediction: Contents
25:22	Bayesian Sequence Prediction: Abstract
25:52	Uncertainty and Probability
27:39	Frequency Interpretation: Counting
28:35	Objective Interpretation: Uncertain Events
29:31	Subjective Interpretation: Degrees of Belief
30:49	Bayes' Famous Rule
33:36	Example: Bayes' and Laplace's Rule
36:28	Example: Bayes' and Laplace's Rule
40:22	Exercise 1: Envelope Paradox
42:32	Exercise 2: Con¯rmation Paradox
44:40	Notation: Strings & Probabilities
45:46	The Bayes-Mixture Distribution »
48:09	Relative Entropy
50:45	Proof of the Entropy Bound
52:11	Posterior Convergence
55:13	Sequential Decisions
57:07	Loss Bounds
60:55	Proof of Instantaneous Loss Bounds
63:01	Generalization: Continuous Probability Classes M
70:46	Bayesian Sequence Prediction: Summary

Lecture rating

People found this lecture:
Worth seeing
because it is:
Valuable and informative
Well presented
Easily understandable
Acceptably recorded
You need to login to cast your vote.

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.