A Curated List of Resources for Starting Your AI/ML Journey

Last updated: Sep 20, 2025

Navigating the vast landscape of Machine Learning can be a daunting task. This curated list of highly-regarded resources is designed to guide your journey with clarity and depth. It includes foundational visualizations, practical coding tutorials, and insightful blogs from leading researchers.

Foundation

Understanding the core mathematical and conceptual underpinnings of neural networks is crucial. These resources excel at building a solid foundation and intuition.

Textbooks

Standard textbooks in the field:

• “Deep Learning” by Ian Goodfellow, Yoshua Bengio, and Aaron Courville.
• “The Elements of Statistical Learning” by Trevor Hastie, Robert Tibshirani, and Jerome Friedman.
• “An Introduction to Statistical Learning” by Gareth James, Daniela Witten, Trevor Hastie, and Robert Tibshirani.

Visualization

3Blue1Brown by Grant Sanderson provides exceptional math visualizations. The Neural Networks series is a great starting point for beginners.

• Link to Neural Networks Playlist

Practical Tutorials

Move from theory to practice with these resources that guide you from theory to writing code.

• Andrej Karpathy’s “Let’s build GPT”: A must-watch series for deep learning practitioners. Karpathy builds a complete GPT from scratch in Python.

• Sebastian Raschka’s Channel and Blogs: Provides practical tutorials, paper deep dives, and explanations of concepts

Essential Blogs

Reading directly from experienced researchers and engineers provides diverse and valuable perspectives into the field.

• The Bitter Lesson: Probably the single most popular blog post in the field of AI

• Sander Dieleman: Insights into generative modeling

Keeping Up

The field moves fast. These resources help you stay current with the latest breakthroughs.

• Bycloud: Provides quick summaries of the latest and most exciting research papers.

• Julia Turc: Explain the latest papers and trends in machine learning.

• Yannic Kilcher: Offers thorough technical breakdowns of recent and influential research papers.

This list is not exhaustive, but it provides a solid foundation for anyone building a robust understanding of machine learning. Happy learning!