Глубинное обучение (курс лекций)/2020

Материал из MachineLearning.

(Различия между версиями)
Перейти к: навигация, поиск
(Новая: __NOTOC__ This is an introductory course on deep learning models and their application for solving different applied problems of image and text analysis. '''Instructors''': [[Участ...)
(Lectures and seminars)
(9 промежуточных версий не показаны.)
Строка 10: Строка 10:
Anytask invite code: ldQ0L2R
Anytask invite code: ldQ0L2R
-
For questions: [course chat in Telegram]
+
Course chat in Telegram: [https://t.me/joinchat/FIB6dhxS8U6wRFI-TDMNSA link]
== Rules and grades ==
== Rules and grades ==
Строка 35: Строка 35:
!Date !! No. !! Topic !! Materials
!Date !! No. !! Topic !! Materials
|-
|-
-
| multicolumns=2|11 Sep. 2020 || multicolumn=2,align="center"|1 || Introduction. Fully-connected networks. ||
+
| rowspan="2"|11 Sep. 2020 || rowspan="2" align="center"| 1 || Introduction. Fully-connected networks. ||
 +
|-
 +
| Matrix calculus, automatic differentiation. || [https://drive.google.com/file/d/1Yu790uIPyxp9JIyysxfJDor_LJQu83gQ/view?usp=sharing Synopsis]
 +
|-
 +
| rowspan="2"|18 Sep. 2020 || rowspan="2" align="center"| 2 || Stochastic optimization for neural networks, drop out, batch normalization. ||
 +
|-
 +
| Convolutional neural networks, basic architectures. || [https://drive.google.com/file/d/1uSVdPsn5wznk510gS9N1K9DXITpxNFXt/view?usp=sharing Presentation]
 +
|-
 +
| 25&nbsp;Sep.&nbsp;2020 || align="center"| 3 || Pytorch and implementation of convolutional neural networks. || [https://github.com/nadiinchi/dl_labs/blob/master/lab_cnn_english.ipynb ipynb 1]<br> [https://github.com/nadiinchi/dl_labs/blob/master/loss_surfaces_lab/lab_loss_surfaces.ipynb ipynb 2]<br>
 +
[https://github.com/nadiinchi/dl_labs/blob/master/lab_pytorch.ipynb ipynb 3]
 +
|-
 +
| 02&nbsp;Oct.&nbsp;2020 || align="center"| 4 || Semantic image segmentation || [https://yadi.sk/d/jel16JzCmHLgBQ Presentation (pdf)]<br>[https://portrait.nizhib.ai/ Portrait Demo] ([https://github.com/nizhib/portrait-demo source])
 +
|-
 +
| 09&nbsp;Oct.&nbsp;2020 || align="center"| 5 || Object detection || [https://yadi.sk/i/vmJJgDAAvtY6Pw Presentation (pdf)]<br>[https://yadi.sk/i/5gLFLx1R7Qfjjg DS Bowl 2018 (pdf)]
 +
|-
 +
| 16&nbsp;Oct.&nbsp;2020 || align="center"| 6 || Neural style transfer. || [https://yadi.sk/i/Hp9wbpaIEHz_pw Presentation]
 +
|-
 +
| 23&nbsp;Oct.&nbsp;2020 || align="center"| 7 || Recurrent neural networks. || [https://drive.google.com/file/d/1KvSzzctOjRhYwJH_9LJJeZhMp4USTcDV/view?usp=sharing Presentation]
|-
|-
-
| || || Matrix calculus, automatic differentiation. || [https://drive.google.com/file/d/1Yu790uIPyxp9JIyysxfJDor_LJQu83gQ/view?usp=sharing Synopsis]
 
|}
|}
-
 
== Arxiv ==
== Arxiv ==

Версия 08:51, 27 октября 2020

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

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

The timetable in Autumn 2020: Fridays, lectures begin at 10-30, seminars begin at 12-15, zoom-link

Lectures and seminars video recordings: link

Anytask invite code: ldQ0L2R

Course chat in Telegram: link

Rules and grades

TBA

Lectures and seminars

Date No. Topic Materials
11 Sep. 2020 1 Introduction. Fully-connected networks.
Matrix calculus, automatic differentiation. Synopsis
18 Sep. 2020 2 Stochastic optimization for neural networks, drop out, batch normalization.
Convolutional neural networks, basic architectures. Presentation
25 Sep. 2020 3 Pytorch and implementation of convolutional neural networks. ipynb 1
ipynb 2

ipynb 3

02 Oct. 2020 4 Semantic image segmentation Presentation (pdf)
Portrait Demo (source)
09 Oct. 2020 5 Object detection Presentation (pdf)
DS Bowl 2018 (pdf)
16 Oct. 2020 6 Neural style transfer. Presentation
23 Oct. 2020 7 Recurrent neural networks. Presentation

Arxiv

2019

2017

2016

Личные инструменты