Statistical learning theory — различия между версиями
Материал из Wiki - Факультет компьютерных наук
Bbauwens (обсуждение | вклад) м |
Bbauwens (обсуждение | вклад) м |
||
| Строка 2: | Строка 2: | ||
[https://www.dropbox.com/s/r5u7gl33berpokv/syllabusStatisticalLearning.pdf?dl=0 Syllabus for the 1st module] | [https://www.dropbox.com/s/r5u7gl33berpokv/syllabusStatisticalLearning.pdf?dl=0 Syllabus for the 1st module] | ||
| − | |||
== Homework == | == Homework == | ||
| − | + | [https://www.dropbox.com/s/1np7hoiwv2ga4yy/homework.pdf?dl=0 Homework module 1] | |
| − | The deadline for submission is Thursday 12th of | + | The deadline for submission is Thursday 12th of Oktober. |
| − | + | Defenses of the homework will happen from 13th of Okt. till 30 Okt. | |
== Project == | == Project == | ||
| Строка 14: | Строка 13: | ||
Will be placed here. | Will be placed here. | ||
The deadline for submission is Saturday 21th of Okt. | The deadline for submission is Saturday 21th of Okt. | ||
| − | |||
== Course materials == | == Course materials == | ||
| − | |||
{| class="wikitable" | {| class="wikitable" | ||
| Строка 25: | Строка 22: | ||
| 5 sept || PAC-learning and VC-dimension: definitions || [https://www.dropbox.com/s/xm4ijvc447htosw/1lect.pdf?dl=0 1st and 2nd lecture] Updated on 13th of Sept. | | 5 sept || PAC-learning and VC-dimension: definitions || [https://www.dropbox.com/s/xm4ijvc447htosw/1lect.pdf?dl=0 1st and 2nd lecture] Updated on 13th of Sept. | ||
|| [https://www.dropbox.com/s/in3bdva76mni16m/1seminar.pdf?dl=0 Problem list 1] | || [https://www.dropbox.com/s/in3bdva76mni16m/1seminar.pdf?dl=0 Problem list 1] | ||
| − | |||
|- | |- | ||
| 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, 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] | | 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 || Agnostic PAC-learning and Computational learning theory || || | | 26 sept || Agnostic PAC-learning and Computational learning theory || || | ||
| − | |||
|- | |- | ||
| 3 okt || Boosting: the adaBoost algorithm || || | | 3 okt || Boosting: the adaBoost algorithm || || | ||
| − | |||
|- | |- | ||
| 10 okt || Boosting: several other algorithms || || | | 10 okt || Boosting: several other algorithms || || | ||
| − | |||
|- | |- | ||
| 17 okt || Online learning algorithms || || | | 17 okt || Online learning algorithms || || | ||
| − | |||
| − | |||
|- | |- | ||
|} | |} | ||
Версия 12:23, 30 сентября 2017
General Information
Homework
Homework module 1 The deadline for submission is Thursday 12th of Oktober. Defenses of the homework will happen from 13th of Okt. till 30 Okt.
Project
Will be placed here. The deadline for submission is Saturday 21th of Okt.
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 | ||
|---|---|---|---|---|---|---|---|
| |
Bruno Bauwens | 15:05–18:00 | 15:05–18:00 | Room 620 | |||
| |
Quentin Paris |
