On-line linear learning algorithms

author: Nicolò Cesa-Bianchi, Università degli Studi di Milano

Description

Prediction with expert advice. Learning with linear experts. The Perceptron algorithm and its extensions. On-line learning with kernels. Mistake bounds. From mistake bounds to risk bounds.

Categories

Top: Computer Science: Machine Learning: On-line Learning

You might be experiencing some problems with Your Video player.

*Slides*
0:02	On-Line Learning
0:25	Background
9:09	Outline
11:41	Binary prediction
13:52	The role of experts
17:24	A simple example
20:10	A more general prediction model
23:04	On-line prediction with expert advice
26:38	Regret
31:06	On-line prediction with expert advice
31:25	Regret
31:45	Weighted average forecasters
35:37	Convex loss functions
37:28	Potential-based forecasters
37:47	Convex loss functions
41:22	Blackwell condition
42:27	Gradient descent interpretation
43:41	Regret
43:48	Gradient descent interpretation
44:44	Blackwell condition
44:57	Gradient descent interpretation

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.