Skip to content

index.md

Latest commit

 

History

History
33 lines (27 loc) · 1.72 KB

index.md

File metadata and controls

33 lines (27 loc) · 1.72 KB

Deep Learning

Theory

  1. Introduction.
  2. Data-driven approaches.
  3. Simple linear classifier, Loss function.
  4. Backpropagation and NN.
  5. Multilayer NN, Activation, Loss.
  6. Normalization, Convolution.
  7. Recurrent Neural Networks.

Applications

  1. Semantic segmentation, Keypoint detection, and Object detection.
  2. Text-to-Speech.
  3. Natural Language Processing - BERT and The History Behind It.
  4. Data management (CVAT).
  5. DL deployment instruments and challenges.

Practice

  1. Task #1 - Simple data-driven approach and results.
  2. How to use training frameworks:
  1. Task #2 - Multilayer neural network and results.
  2. Symbol 'H' to sequence 'HELLO' with RNN: Download.
  3. Test results.

Сomputational resource

  1. Google Colab
  2. Google Cloud Platform