Глубинное обучение (курс лекций)/2019

Материал из MachineLearning.

(Различия между версиями)
Перейти к: навигация, поиск
Строка 4: Строка 4:
'''Instructors''': [[Участник:Kropotov|Dmitry Kropotov]], [[Участник:Victor Kitov|Victor Kitov]], Nadezhda Chirkova, Oleg Ivanov and Evgeny Nizhibitsky.
'''Instructors''': [[Участник:Kropotov|Dmitry Kropotov]], [[Участник:Victor Kitov|Victor Kitov]], Nadezhda Chirkova, Oleg Ivanov and Evgeny Nizhibitsky.
-
E-mail for questions: ''bayesml@gmail.com''. Please include in subject the tag [CMC DL19].
+
The timetable in Autumn 2019: Mondays, lectures begin at 10-30, seminars begin at 12-15, room 526b.
-
 
+
-
The timetable in Spring 2019: Fridays, most lectures begin at 14-35, seminars begin at 16-20. Exact place and time are given in tables below.
+
-
 
+
-
[https://t.me/joinchat/DEBCqg_Y08322lq6WRqONg Link to a chat]
+
-
 
+
-
== Exam ==
+
-
The final exam is scheduled on 14th of June, r.613, start at 13-00. The exam will be organized in English.
+
-
 
+
-
[https://drive.google.com/file/d/1xih5XN3ybQm_0H5p9Dv20U3Ak4qny2uU/view?usp=sharing Exam questions]
+
== Rules and grades ==
== Rules and grades ==
-
We have 5 practical assignments during the course. For each assignment, a student may get up to 10 points + possibly bonus points. A student is allowed to upload his fulfilled assignment during one week after deadline with grade reduction of 0.2 points per day. All assignments are prepared in English.
+
We have several practical assignments during the course. For each assignment, a student may get up to 10 points + possibly bonus points. A student is allowed to upload his fulfilled assignment during one week after deadline with grade reduction of 0.2 points per day. All assignments are prepared in English.
Also each student may give a small 10-minutes talk in English on some recent DL paper. For this talk a student may get up to 5 points.
Also each student may give a small 10-minutes talk in English on some recent DL paper. For this talk a student may get up to 5 points.
-
The total grade for the course is calculated as follows: Round-up (0.3*<Exam_grade> + 0.7*<Semester_grade>), where <Semester_grade> = min(10, (<Assignments_total_grade> + <Talk_grade>) / 5.5), <Exam_grade> is a grade for the final exam (up to 10 points).
+
The total grade for the course is calculated as follows: Round-up (0.3*<Exam_grade> + 0.7*<Semester_grade>).
 +
<!--, where <Semester_grade> = min(10, (<Assignments_total_grade> + <Talk_grade>) / 5.5), <Exam_grade> is a grade for the final exam (up to 10 points).
{| class="standard"
{| class="standard"
!Final grade !! Total grade !! Necessary conditions
!Final grade !! Total grade !! Necessary conditions
Строка 30: Строка 22:
| 3 || >=4 || 3 practical assignments are done, exam grade >= 4
| 3 || >=4 || 3 practical assignments are done, exam grade >= 4
|-
|-
-
|}
+
|}-->
== Practical assignments ==
== Practical assignments ==
-
Practical assignments are provided on course page in ''anytask.org''. Invite code: bgvpqVE
+
Practical assignments are provided on course page in ''anytask.org''. Invite code: ?????
== Lectures ==
== Lectures ==
{| class="standard"
{| class="standard"
-
!Date !! No. !! Place and time !! Topic !! Materials
+
!Date !! No. !! Topic !! Materials
|-
|-
-
| 15&nbsp;Feb.&nbsp;2019 || align="center"|1 || r.685, 14-35 || Introduction. Automatic differentiation. ||
+
| 02&nbsp;Sep.&nbsp;2019 || align="center"|1 || Introduction. Fully-connected networks. Automatic differentiation. ||
-
|-
+
-
| 22&nbsp;Feb.&nbsp;2019 || align="center"|2 || r.685, 14-35 || Optimization and regularization methods for neural networks ||
+
-
[http://jmlr.org/papers/v15/srivastava14a.html DropOut]<br>
+
-
[https://arxiv.org/abs/1502.03167 Batch Normalization]<br>
+
-
[http://proceedings.mlr.press/v9/glorot10a/glorot10a.pdf Glorot initialization]<br>
+
-
[https://arxiv.org/abs/1412.6980 ADAM optimizer]
+
-
|-
+
-
| 01&nbsp;Mar.&nbsp;2019 || align="center"|3 || r.526b, 14-35 || Convolutional neural networks for image classification problem ||
+
-
[https://drive.google.com/file/d/1DkKyDUvo5JOm1u9Lghfv-Jh1vB3297t7/view?usp=sharing Slides (pptx)]
+
-
|-
+
-
| 15&nbsp;Mar.&nbsp;2019 || align="center"|4 || r.526b, 16-20 || Convolutional neural networks for image segmentation problem || [https://yadi.sk/i/xkw00-mr-Zk_Kw Slides (pdf)], [https://yadi.sk/i/n9O_1RP3QxGb8A DS Bowl 2018 (pdf)]
+
-
|-
+
-
| 22&nbsp;Mar.&nbsp;2019 || align="center"|5 || r.526b, 14-35 || Object detection and localization on images || [https://yadi.sk/i/_WDz9dcyvwCDIA Slides (pdf)]
+
-
|-
+
-
| 29&nbsp;Mar.&nbsp;2019 || align="center"|6 || r.523 (instead of r.645), 12-50 || Image style transfer || [https://yadi.sk/i/wPgb4U4XGX2GsQ Main models] <br> [https://yadi.sk/i/UNTi7b4yG4CHeg Enhancements 1] <br> [https://yadi.sk/i/RAiySn6LKdGIyw Enhancements 2] <br> [https://yadi.sk/i/nVgEu5taI52s1w Multi-style online models] <br> [https://yadi.sk/i/seDJTnns2_lzBw Patch-based style transfer]
+
-
|-
+
-
| 05&nbsp;Apr.&nbsp;2019 || align="center"|7 || r.526b, 14-35 || Recurrent neural networks || [https://drive.google.com/file/d/1KvSzzctOjRhYwJH_9LJJeZhMp4USTcDV/view?usp=sharing Slides (pdf)]
+
-
|-
+
-
| 12&nbsp;Apr.&nbsp;2019 || align="center"|8 || r.526b, 14-35 || Attention mechanism ||
+
-
[https://drive.google.com/file/d/1uHT_Xe1MaNv3NSO7Ns79K43KsGibcavc/view?usp=sharing Slides (pptx)]
+
-
[https://drive.google.com/file/d/1ritIJp74SGDs1yE4Rq3bXYvDELCw4enr/view?usp=sharing Slides 2 (pdf)]
+
-
|-
+
-
| 19&nbsp;Apr.&nbsp;2019 || align="center"|9 || r.526b, 14-35 || Generative adversarial networks || [https://yadi.sk/i/SQynrJ3pNrEZLw Slides (pdf)]
+
-
|-
+
-
| 17&nbsp;May&nbsp;2019 || align="center"|10 || r.526b, 14-35 || Students' presentations ||
+
|-
|-
|}
|}
Строка 72: Строка 39:
{| class="standard"
{| class="standard"
-
!Date !! No. !! Place and time !! Topic !! Need laptops !! Materials
+
!Date !! No. !! Topic !! Need laptops !! Materials
-
|-
+
-
| 15&nbsp;Feb.&nbsp;2019 || align="center"|1 || r.685, 16-20 || Automatic differentiation. || No || [https://www.cs.ox.ac.uk/files/723/NA-08-01.pdf Notes on backprop]
+
-
|-
+
-
| 22&nbsp;Feb.&nbsp;2019 || align="center"|2 || r.685, 16-20 || Introduction to Azure and Pytorch || Yes || [https://github.com/nadiinchi/dl_labs/blob/master/lab_pytorch.ipynb Notebook]
+
-
|-
+
-
| 01&nbsp;Mar.&nbsp;2019 || align="center"|3 || r.526b, 16-20 || Convolutional neural networks for MNIST || Yes ||
+
-
|-
+
-
| 22&nbsp;Mar.&nbsp;2019 || align="center"|4 || r.526b, 16-20 || Semantic segmentation applications || No || [https://github.com/nadiinchi/dl_labs/blob/master/lab_semseg_en.ipynb Notebook], [https://github.com/nizhib/portrait-demo Portrait Demo]
+
-
|-
+
-
| 29&nbsp;Mar.&nbsp;2019 || align="center"|5 || r.526b, 14-35 || Image style transfer || No ||
+
-
|-
+
-
| 05&nbsp;Apr.&nbsp;2019 || align="center"|6 || r.526b, 16-20 || Recurrent neural networks || Yes ||
+
-
|-
+
-
| 12&nbsp;Apr.&nbsp;2019 || align="center"|7 || r.526b, 16-20 || Attention mechanism || Yes ||
+
-
|-
+
-
| 19&nbsp;Apr.&nbsp;2019 || align="center"|8 || r.526b, 16-20 || Generative adversarial networks || No ||
+
|-
|-
-
| 17&nbsp;May&nbsp;2019 || align="center"|9 || r.526b, 16-20 || Students' presentations || No ||
+
| 9&nbsp;Sep.&nbsp;2019 || align="center"|1 || Introduction to Pytorch || Yes ||
|-
|-
|}
|}

Версия 01:08, 2 сентября 2019

This is an introductory course on deep learning models and their application for solving different problems of image and text analysis.

Instructors: Dmitry Kropotov, Victor Kitov, Nadezhda Chirkova, Oleg Ivanov and Evgeny Nizhibitsky.

The timetable in Autumn 2019: Mondays, lectures begin at 10-30, seminars begin at 12-15, room 526b.

Rules and grades

We have several practical assignments during the course. For each assignment, a student may get up to 10 points + possibly bonus points. A student is allowed to upload his fulfilled assignment during one week after deadline with grade reduction of 0.2 points per day. All assignments are prepared in English.

Also each student may give a small 10-minutes talk in English on some recent DL paper. For this talk a student may get up to 5 points.

The total grade for the course is calculated as follows: Round-up (0.3*<Exam_grade> + 0.7*<Semester_grade>).

Practical assignments

Practical assignments are provided on course page in anytask.org. Invite code: ?????

Lectures

Date No. Topic Materials
02 Sep. 2019 1 Introduction. Fully-connected networks. Automatic differentiation.

Seminars

Date No. Topic Need laptops Materials
9 Sep. 2019 1 Introduction to Pytorch Yes

Arxiv

2017

2016