puhsu / dl-hse

Materials for the Deep Learning 2 course at HSE AMI

Deep Learning 2

This repo contains homework and lecture slides for the Deep Learning course at the Faculty of Computer Science of HSE University. Previous versions of the course are available at https://github.com/mryab/dl-hse-ami and https://github.com/aosokin/dl_cshse_ami

Syllabus

week 1: Deep Learning best practices

• Lecture by Max Ryabinin (slides)
• PyTorch homework (ipynb)
• Looking for bugs homework (ipynb)

week 2: Computer vision (detection)

• Lecture by Alexander Dyakonov (slides)

week 3: Computer vision (detection2)

• Lecture by Alexander Dyakonov (slides)
• FCOS detector (shw3)

week 4: Neural Fields

• Lecture by Kirill Struminsky (slides)

week 5: Transformers (architectures)

• Lecture by Ivan Rubachev (slides)
• homework: implementing transformer and linear attention (ipynb)

week 6: Transformers (LLMs, interpretability)

• Lecture by Ivan Rubachev (slides)
• BIG homework-1 (readme)

week 7: Generative models (Intro to divergences and GANs)

• Lecture by Aziz Temirkhanov (slides) (Evolution slides)

week 8: Generative Models (VAE, Diffusion)

• Lecture by Aziz Temirkhanov (VAE slides) (Diffusion slides)
• diffusion homework (ipynb)
• big homework (readme)

week 9: Graph neural networks

• Lecture by Gleb Bazhenov (slides)
• Seminar by Oleg Platonov
• gnn homework (ipynb)

week 10: Tabular Deep Learning

• Lecture by Yura Gorihsniy
• BIG homework-2
• tabular homework (ipynb)