This repository provides comprehensive lecture notes, video explanations, and practical code experiments for understanding deep learning concepts. It targets students, researchers, and practitioners looking to deepen their knowledge of various neural network architectures and related tools, offering a structured learning path from foundational concepts to advanced topics like LLMs and diffusion models.

How It Works

The project is structured around distinct deep learning topics, each with accompanying PDF notes, video lectures, and runnable Jupyter notebooks or Python scripts. It emphasizes practical implementation using PyTorch and related libraries like Hugging Face, Einops, and PyTorch Lightning, facilitating hands-on learning and experimentation with core architectures such as MLPs, CNNs, RNNs, Transformers, GANs, and Diffusion Models.

Quick Start & Requirements

• Install dependencies: pip install -r requirements.txt --upgrade
• Requires Python and a virtual environment (conda or venv).
• Links: Official Docs

Highlighted Details

• Covers a wide range of deep learning topics from supervised to unsupervised learning, including LLMs and diffusion models.
• Provides practical code examples for architectures like MLPs, CNNs, RNNs, Transformers, GANs, and Autoencoders.
• Includes tutorials on essential tools like PyTorch, Hugging Face, Gradio, and model serving with ONNX and TensorRT.
• Offers video lectures and detailed PDF notes for each topic.

Maintenance & Community

• Maintained by Rowel Atienza.
• Includes citation information for academic use.

Licensing & Compatibility

• License: MIT.
• Permissive for commercial use and integration into closed-source projects.

Limitations & Caveats

The repository's content is organized by version (e.g., 2023-2024, 2022), suggesting potential for outdated practices or dependencies in older versions. Some advanced topics like "Unsupervised Learning" are marked as "Soon" in older sections.