Intro to DL Blended — различия между версиями

Версия 20:33, 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:

1. SGD variations: Moment, RMSProp, Adam with explanation
2. Description of backprop and proof of its efficiency
3. Gradient of a dense layer in matrix notation (with proof)
4. Typical CNN architecture, purpose of each layer, how to do backprop
5. Inception V3 architecture choices
6. Gradient of RNN cell (with proof)