en-de
en-es
en-fr
en-sl
en
en-zh
0.25
0.5
0.75
1.25
1.5
1.75
2
How to predict with Bayes, MDL, and Experts
Published on 2007-02-257560 Views
Most passive Machine Learning tasks can be (re)stated as sequence prediction problems. This includes pattern recognition, classification, time-series forecasting, and others. Moreover, the understandi
Related categories
Presentation
How to Predict with Bayes, MDL, and Experts00:44
Overview01:24
Table of Contents07:59
Philosophical Issues: Contents08:44
Philosophical Issues: Abstract09:21
On the Foundations of Machine Learning09:22
Example 1: Probability of Sunrise Tomorrow11:50
Example 2: Digits of a Computable Number15:29
Example 3: Number Sequences17:15
Occam's Razor to the Rescue20:57
Foundations of Induction21:58
Problem Setup23:22
Dichotomies in Machine Learning25:15
Sequential/online predictions27:53
Bayesian Sequence Prediction: Contents30:16
Bayesian Sequence Prediction: Abstract31:11
Uncertainty and Probability31:13
Frequency Interpretation: Counting32:01
Objective Interpretation: Uncertain Events33:12
Subjective Interpretation: Degrees of Belief35:01
Bayes' Famous Rule37:31
Example: Bayes' and Laplace's Rule41:14