Intro to DL Blended: различия между версиями
Перейти к навигации
Перейти к поиску
Zimovnov (обсуждение | вклад) Нет описания правки |
Zimovnov (обсуждение | вклад) Нет описания правки |
||
| Строка 8: | Строка 8: | ||
Final grade = 75% cumulative grade + 25% final exam | Final grade = 75% cumulative grade + 25% final exam | ||
'''Additional project:''' | '''Additional project:''' | ||
| Строка 15: | Строка 13: | ||
Homework with Kaggle competition: https://docs.google.com/document/d/1kTMYq21UFqZOqftjKAPq8G7RRkO7kX3MomsVIVhW830/edit?usp=sharing | Homework with Kaggle competition: https://docs.google.com/document/d/1kTMYq21UFqZOqftjKAPq8G7RRkO7kX3MomsVIVhW830/edit?usp=sharing | ||
Release date: | Release date: 18-02-2020 00:00 | ||
Deadline: | Deadline: 03-03-2020 00:00 | ||
'''Exam:''' | '''Exam:''' | ||
| Строка 29: | Строка 27: | ||
# Description of auto-encoder, application to images | # Description of auto-encoder, application to images | ||
# Gradient of RNN cell (with proof) | # Gradient of RNN cell (with proof) | ||
Версия от 08:36, 18 февраля 2020
Course program:
https://www.hse.ru/data/2018/06/05/1150113338/program-2129241367-JndYcQjSAq.pdf
Grading:
Cumulative grade = 80% online course + 20% additional project
Final grade = 75% cumulative grade + 25% final exam
Additional project:
Homework with Kaggle competition: https://docs.google.com/document/d/1kTMYq21UFqZOqftjKAPq8G7RRkO7kX3MomsVIVhW830/edit?usp=sharing
Release date: 18-02-2020 00:00
Deadline: 03-03-2020 00:00
Exam:
In writing, theoretical questions, for instance:
- SGD variations: Moment, RMSProp, Adam with explanation
- Description of backprop and proof of its efficiency (линейное время работы)
- Gradient of a dense layer in matrix notation (with proof)
- Typical CNN architecture, purpose of each layer, how to do backprop
- Inception V3 architecture choices
- Description of auto-encoder, application to images
- Gradient of RNN cell (with proof)