Machine Learning Summer School 2006 - Canberra

Introduction to Learning Theory

author: Olivier Bousquet, Google

Description

The goal of this course is to introduce the key concepts of learning theory. It will not be restricted to Statistical Learning Theory but will mainly focus on statistical aspects. Instead of giving detailed proofs and precise statements, this course will aim at providing some useful conceptual tools and ideas useful for practitioners as well as for theoretically-driven people.

Categories

Top: Computer Science: Machine Learning: Statistical Learning

You might be experiencing some problems with Your Video player.

*Slides*
0:00	Introduction to Learning Theory
2:35	Outline
3:35	Goal of this course
4:10	Not covered
4:56	Learning Theory: What?
6:15	Some more definitions
8:17	What is a good theory?
10:07	What is Learning?
11:52	Recursion
13:03	Recursion 01
13:41	Learning Theory: Why?
14:59	Inductive principles
16:03	Example 1: Probability of Sunrise Tomorrow
16:42	Example 1: Probability of Sunrise Tomorrow 01
20:05	Example 2: extend a sequence of integers
20:37	Example 2: sequence of integers
26:16	Example 3: sequence of integers [Hutter]
27:26	Example 4: sequence of digits [Hutter]
30:29	Inductive Principle
32:46	Probability: a nice tool for reasoning
33:59	Probabilities as Frequencies
36:48	Probabilities as Intrinsic Properties
37:23	Probabilities as Degrees of Belief
38:45	Bayes' Rule
40:20	Probabilities and Proofs
41:32	The need for assumptions
42:36	The need for assumptions (2)
44:30	Settings
46:35	Settings vs Assumptions
50:27	Settings and Algorithms
51:03	Data Generation Mechanisms
53:08	Protocols
53:26	Success Measures
54:23	Type of analysis

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.