Computational Intelligence, SS08 2 VO 442.070 + 1 RU 708.070 last updated:
General
Course Notes (Skriptum)
Online Tutorials
Practical Course Slides
Homework
 Assignments Scores Guidelines Archive
Exams
Animated Algorithms
Interactive Tests
Key Definitions
News
mailto:webmaster

# Homework 24: Relationship between the true error of a hypothesis and its error on the training set.

[Points: 8; Issued: 2005/03/18; Deadline: 2005/04/28; Tutor: Stefan Rath; Infohour: 2005/04/25, 12:00-13:00, Seminarraum IGI; Einsichtnahme: 2005/05/16, 12:00-13:00, Seminarraum IGI; Download: pdf; ps.gz]

Construct for every a probability measure on and a class of hypotheses for which you can prove: for every there exists a nonempty list of examples with for all in and a hypothesis so that and . The construction and the proof should be clearly structured, and consist of complete sentences in perspicuous logical relationship.

### Note:

You can get up to 2 extra -points if you can arrange your construction so that the same and the same can be chosen for all .