Intro to DL Blended: различия между версиями

Материал из Wiki - Факультет компьютерных наук
Перейти к навигации Перейти к поиску
Новая страница: «'''Program:''' https://www.hse.ru/data/2018/06/05/1150113338/program-2129241367-JndYcQjSAq.pdf '''Grading:''' Cumulative grade = 80% online course + 20% addition…»
 
Нет описания правки
Строка 1: Строка 1:
'''Program:'''
'''Course program:'''
https://www.hse.ru/data/2018/06/05/1150113338/program-2129241367-JndYcQjSAq.pdf
https://www.hse.ru/data/2018/06/05/1150113338/program-2129241367-JndYcQjSAq.pdf


Строка 8: Строка 8:
'''Additional project:'''
'''Additional project:'''
Homework with Kaggle competition
Homework with Kaggle competition
'''Exam:'''
In writing, theoretical questions, for instance:
- SGD variations: Moment, RMSProp, Adam with explanation
- Description of backprop and proof of its efficiency
- 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
- Gradient of RNN cell (with proof)

Версия от 17:30, 3 марта 2019

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

Exam: In writing, theoretical questions, for instance: - SGD variations: Moment, RMSProp, Adam with explanation - Description of backprop and proof of its efficiency - 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 - Gradient of RNN cell (with proof)