Intro to DL Blended

Материал из Wiki - Факультет компьютерных наук
Перейти к: навигация, поиск

Course program:


Cumulative grade = 80% online course + 20% additional project

Final grade = 75% cumulative grade + 25% final exam


Additional project:

Homework with Kaggle competition:

Release date: 10-03-2019 16:00

Deadline: 24-03-2019 03:00


In writing, theoretical questions, for instance:

  1. SGD variations: Moment, RMSProp, Adam with explanation
  2. Description of backprop and proof of its efficiency (линейное время работы)
  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. Description of auto-encoder, application to images
  7. Gradient of RNN cell (with proof)


1. Keras Tutorial