Deep Learning Bootcamp

Bootcamp covering introductory and advanced topics of Deep Learning. Twice per year (Summer and Winter).

Materials and Recordings on GitHub.

Since 2016, LauzHack has organized hackathons at EPFL in Lausanne, Switzerland. We also organize tech talks during the school year.

In Summer 2024, we organized the first Deep Learning Bootcamp. It consisted of 9 days with 2-4 hours per day and covered both introductory and advanced topics.

Topics:

  • Introduction: PyTorch, Deep Learning concept, Datasets, Optimizers, Schedulers, Loss Functions, FC, CNN, RNN, Transformer, Python Dev Tools, Git, WandB, Hydra, R&D Coding

  • Deep Learning in Audio: Overview of different tasks (ASR, Source Separation, TTS, VC), Voice Biometry (a.k.a. deepfake detection), Neural Vocoders, GANs, GNNs

  • NLP: Introduction to NLP, Past vs Modern approaches, modeling texts with RNNs and Transformer, seq2seq machine translation, text classification (BERT), text generation (GPT), and text generation at scale (LLMs)

  • CV: object detection, image segmentation, and 3D vision (basics of volume rendering and implicit surface representations, NeRFs, NeuS, DeepSDF, and their applications)

  • Guests’ Material: DeepRL, XAI (Model interpretation), On-Device Learning, Distributed / Decentralized DL

This bootcamp was originally my initiative and I was the main organizer. My LauzHack colleagues, Eric and Parsa, helped me a lot. We also invited many PhD guests from EPFL and ETH Zurich laboratories.

This Winter, we will do a Winter Edition.