Jupyter notebook repository for self-learning

I hope this fits the posting guidelines here: For self-learners in the wider area of AI/ML/DL/NLP but also data science in general, we are building a repository of Jupyter notebooks. The repository can be seen as an open, large-scale, interactive textbook – well, hopefully becoming large in the future. The original purpose of these notebooks was to serve as supplementary learning materials for students in my university courses, but now I just share them with everyone.

All topics related to deep learning and neural networks use PyTorch for code examples or full-fledged tutorials. Here are just some current examples:

* Transformers and Attention

* Recurrent Neural Networks – An Introduction

* Working with Batches for Sequence Tasks

* Handwritten Digit Recognition with ANNs

* Text Classification with RNNs

* Data Batching for Training LLMs

* Masking in Sequence Models

* Mixture of Experts (MoE)

* Token Indexing with Vocabularies

Right now, the repository is more targeted toward beginners, with a strong focus on detailed explanations and illustrations. However, we have more advanced topics planned and already in the pipeline. So, yeah, you’re welcome to check it out. We actually created a Discord server for announcement, support, and feedback, but I feel posting the link here might violate some guidelines :).