Skip to content

markovka17/apdl

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

31 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Applied Problems of Deep Learning (APDL)

  • Lecture and seminar materials for each week are in ./week* folders, see README.md for materials and instructions
  • Any technical issues, ideas, bugs in course materials, contribution ideas - add an issue

Syllabus

  • week01 Introduction to Digital Signal Processing

    • Lecture: Signals, Fourier transform, Spectrograms, MelScale
    • Seminar: Intro in PyTorch, AudioMNIST Classification
  • week02 Automatic Speech Recognition

    • Lecture: Metrics, Attention, LAS, CTC, BeamSearch
    • Seminar: QuartzNet and CTC based ASR
  • week03 Text to Speech

    • Lecture: Tacotron2, WaveNet, Parallel WaveGAN
    • Seminar: WaveNet based Vocoder
  • week04 Language Modeling

    • Lecture: Word Embeddings, Language Modeling
    • Seminar: POS tagging based on bi-LSTM, Text Classification based on CNN+Attention, and Neural LMs
  • week05 Machine Translation

    • Lecture: Encoder-Decoder framework, Attention, Transformer
    • Seminar: Transformer in details
  • week06 Transfer Learning

    • Lecture: ELMo, BERT
    • Seminar: Intro to HuggingFace
  • week07 Facial Recognition

    • Lecture: Triplet loss, Angular Softmax, ArcFace
    • Seminar: Metric Learning with CIFAR100
  • week08 Segmentation

    • Lecture: Upsampling, U-Net, HRNet, Metrics
    • Seminar: Cell Segmentation
  • week09 Object Detection

    • Lecture: R-CNN, Fast R-CNN, Faster R-CNN, YOLO
    • Seminar: People Detection
  • week10 How to deploy your neural network?

    • Lecture: Quantization, Pruning, Distilation
    • Seminar: Flask and torchserve for model deployment

Homeworks

  • ASR Implementation of a small ASR model based on QuartzNet
  • MT Implementation of a small MT model based on Transformer
  • CV Implementation of a small segmentation model

Contributors & course staff

Course materials and teaching (mainly) performed by

About

Applied Problems of Deep Learning

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published