LauzHack bootcamp

A repository for the Deep Learning Bootcamp (Summer 2025 Edition) from the Lausanne hackathon organisers.

Deep Learning Bootcamp

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

This is a repository for our Deep Learning Bootcamp (Summer 2025 Edition). For previous editions, see Previous Editions section.

day01 Introduction to Deep Learning and PyTorch
- Lecture: Introduction to bootcamp and Deep Learning
- Seminar: Introduction to pytorch
day02 Basic Model Architectures
- Lecture: Fully-connected and Convolutional Neural Networks, ResNet
- Seminar: Models in pytorch and training pipeline
day03 Recurrent Neural Networks
- Lecture: Recurrent Neural Networks, LSTM, GRU
- Seminar: RNN, LSTM, GRU example
day04 Transformer and Normalization layers. Introduction to NLP.
- Lecture: Transformer. BatchNorm, LayerNorm.
- Seminar: Implementation of Transformer in pytorch
day05 Creating convenient Deep Learning pipelines and clean reproducible code.
- Lecture: Logging, Configuration, Reproducibility, and Project-based code development.
day06 Large Language Models (LLMs) and Brain-inspired LLMs.
- Lecture: Introduction to LLMs and how can we improve them through brain-inspiration.
day07 Multimodal deep learning and deep learning for audio.
- Lecture: Introduction to audio domain. Multimodality and Generative AI. Deepfakes.
- Seminar: Basics of audio processing. Keyword-spotting task implementation.
day08 Source Separation and Deepfake Detection.
- Lecture 1: Diffusion models, Source Separation
- Lecture 2: Deepfake Detection, Self-Supervised Models, Graph Neural Networks
- Seminar 2: Audio anti-spoofing, Graph Neural Networks implementation.

For self-practice, we also propose several Projects.

Bootcamp materials and teaching were delivered by:

👋 Contact 💻 Source