Statistical learning theory — различия между версиями

Материал из Wiki - Факультет компьютерных наук
Перейти к: навигация, поиск
м (3th lecture)
м
Строка 16: Строка 16:
 
|-
 
|-
 
| 12 sept || PAC-learning and VC-dimension: proof of fundamental theorem  ||  || [https://www.dropbox.com/s/wczt02f8linttzu/2seminar.pdf?dl=0 Problem list 2]
 
| 12 sept || PAC-learning and VC-dimension: proof of fundamental theorem  ||  || [https://www.dropbox.com/s/wczt02f8linttzu/2seminar.pdf?dl=0 Problem list 2]
 
  
 
|-
 
|-
| 19 sept || Sauer's lemma, agnostic PAC-learning, structural risk minimization  || [https://www.dropbox.com/s/xf0xz1dlnps90ii/3lect.pdf?dl=0 3th lecture] Updated on the 23th of Sept. || [https://www.dropbox.com/s/x6r2rwbh5qkxat6/3seminar.pdf?dl=0 Problem list 3]
+
| 19 sept || Sauer's lemma, neural networks and agnostic PAC-learning || [https://www.dropbox.com/s/xf0xz1dlnps90ii/3lect.pdf?dl=0 3th lecture] Updated on the 23th of Sept. || [https://www.dropbox.com/s/x6r2rwbh5qkxat6/3seminar.pdf?dl=0 Problem list 3]
  
 
|-
 
|-
| 26 sept ||  Computational learning theory ||  ||  
+
| 26 sept || Agnostic PAC-learning and Computational learning theory ||  ||  
 
+
  
 
|-
 
|-

Версия 15:43, 23 сентября 2017

General Information

Syllabus for the 1st module


Course materials

Date Summary Lecture notes Problem list
5 sept PAC-learning and VC-dimension: definitions 1st and 2nd lecture Updated on 13th of Sept. Problem list 1
12 sept PAC-learning and VC-dimension: proof of fundamental theorem Problem list 2
19 sept Sauer's lemma, neural networks and agnostic PAC-learning 3th lecture Updated on the 23th of Sept. Problem list 3
26 sept Agnostic PAC-learning and Computational learning theory
3 okt Boosting: the adaBoost algorithm
10 okt Boosting: several other algorithms
17 okt Online learning algorithms



A gentle introduction to the materials of the first 3 lectures and an overview of probability theory, can be found in chapters 1-6 and 11-12 of the following book: Sanjeev Kulkarni and Gilbert Harman: An Elementary Introduction to Statistical Learning Theory, 2012.


Office hours

Person Monday Tuesday Wednesday Thursday Friday
1
Bruno Bauwens 15:05–18:00 15:05–18:00 Room 620
2
Quentin Paris