🚀 Resources to Learn AI and Machine Learning

This repository contains a curated list of resources that helped me learn about artificial intelligence, machine learning, neural networks, and large language models (LLMs).

Personal Note: This is my personal learning journey. While there may be other approaches to learning these topics, this path worked well for me and might be helpful for others too.

📚 My Learning Path

• How I Use LLMs by Andrej Karpathy
  A fantastic introduction to practical applications of large language models from one of the field's leading researchers. This video provides an excellent overview of what's possible with LLMs.

• Neural Networks Playlist by 3Blue1Brown
  Grant Sanderson's visual explanations make the mathematics behind neural networks intuitive and accessible. This series builds a solid foundation for understanding how neural networks work.

• Learn PyTorch for Deep Learning in a Day
  A comprehensive crash course on PyTorch fundamentals that gets you coding neural networks quickly. This hands-on approach helps solidify theoretical concepts.

• Practical Deep Learning for Coders by Jeremy Howard
  This course takes a top-down approach to deep learning, teaching you to build state-of-the-art models before diving into the theory. It's perfect for those who learn by doing.

• Neural Networks: Zero to Hero by Andrej Karpathy
  A course that builds neural networks from scratch, helping you understand the fundamentals deeply. Perfect for those who want to truly grasp how these systems work under the hood.

🔍 Specialized Resources for Going Deeper

Transformers and Large Language Models

• Super Study Guide for Transformers and Large Language Models by Afshine Amidi and Shervine Amidi
  A clear, illustrated guide covering key concepts and practical applications of LLMs. Ideal for projects, interviews, or personal learning.

• Attention in Transformers: Concepts and Code in PyTorch by Josh Starmer
  A deep dive into the attention mechanism that powers modern language models, with practical PyTorch implementations.

• Small Language Models (arXiv Paper)
  Research paper exploring the capabilities and applications of smaller, more efficient language models as alternatives to large-scale models.

AI Development and Integration

• Model Context Protocol (MCP) vs API by Norah Sakal
  An explanation of how Model Context Protocol simplifies AI integrations compared to traditional APIs, making it easier to work with language models.

• AI by Hand
  Interactive workbooks for hands-on learning and experimentation with AI models and techniques.

Research and Trends

• Papers with Code Trends
  Stay up-to-date with the latest research papers and their implementations, tracking emerging trends in AI and machine learning.

🤝 Contributing

Found a resource that helped you? Feel free to suggest additional resources by opening an issue or submitting a pull request.

📄 License

This collection of resources is shared under MIT License.