Deep Learning Research

The course covers introductory and advanced deep learning techniques with a research-oriented focus.

• 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
• The current version of the course is conducted in Spring 2026 at the CS Faculty of HSE.

Syllabus

• week01 Introduction to Course. Deep Learning Basics
  • Lecture: Introduction to Course and Deep Learning
  • Seminar: Introduction to pytorch
• week02 FC, CNN, and ResNet
  • Lecture: Fully-Connected Layers, Convolution, ResNet, Fine-Tuning
  • Seminar: Creating and training models in pytorch
• week03 RNN, Normalization, and Dropout
  • Lecture: RNN (+LSTM, GRU), BatchNorm/LayerNorm/Dropout
  • Seminar: Implementation of SketchRNN
• week04 Introduction to NLP and Transformer
  • Lecture: NLP Basics, Tokenization, Embeddings, Transformer
  • Seminar: Implementation of Transformer. HuggingFace basics
• week05 Large Language Models
  • Lecture: Core techniques related to Large Language Models
  • Seminar: HuggingFace basics. vLLM and OpenAI clients
• week06 Deep Learning for Audio
  • Lecture: Tasks Overview, Signal Processing Basics, Automatic Speech Recognition
  • Seminar: Keyword Spotting Implementation, AudioBot (ASR + LLM + TTS)
• week07 AutoEncoders
  • Lecture: AutoEncoders, VAE, VQ-VAE, Text-To-Image, Text-To-Audio
• week08 Diffusion
  • Lecture: Denoising Score Matching, SDE, DDPM, DiT, UNet, Image/Audio Generation
  • Seminar: Diffusers basics.
• week09 Generative Adversarial Networks (GANs)
  • Lecture: Vanilla GAN, LSGAN, WGAN, cGAN, Applications
  • Seminar: Implementation of GAN

Homeworks and Projects

• HW_Basics PyTorch basics, Fine-Tuning, and Ablation Studies.
• HW_NLP Machine Translation, Text Deepfake Detection, HuggingFace.
• HW_Diffusion Diffusion and Super-Resolution.

See our project template.

Resources

• Lecture recordings on YouTube (in russian)

Some of the weeks have English recordings. See the corresponding sub-directories.

Contributors & course staff

Course materials and teaching (in different years) were delivered by:

• Petr Grinberg