ML Resourses

Machine Learning Learning Roadmap

Mathematics Prerequisites

1. Linear Algebra

   • Lecture Course: Gilbert Strang's Lecture Course

2. Probability Theory

   • Course: MIT 6.041

   • Includes Bayesian Inference

3. Calculus

   • High school and college calculus courses are sufficient.

4. Optimization Theory (Optional)

5. Information Theory (Optional)

Classical Machine Learning

1. Course:

   • CS229 by Andrew Ng (or similar)

   • Follow lecture notes and solve problem sets.

2. Reference Books:

   • Pattern Recognition and Machine Learning by Christopher M. Bishop

   • Pattern Classification by Richard O. Duda, Peter E. Hart, and David G. Stork

Deep Learning and Computer Vision

1. Course:

   • CS231n by Stanford (Great lectures and assignments)

2. Reference Book:

   • Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville (Highly recommended for its math and intuition)

MLOps

• Tools: DVC, WandB, MLFlow

Natural Language Processing (NLP)

• Resource: Hugging Face Blogs

Alignment/AI Safety/AI Explainability

• Blogs: Anthropic Blogs (Currently exploring)

Additional Resources

1. Blogs:

   • Lilian Weng's Blog

   • Colah’s Blog

2. Papers:

   • arXiv (Read various research papers)

3. Modern Deep Learning Frameworks:

   • Keras Blog

   • TensorFlow Blog

4. Competitions:

   • Kaggle

5. Cloud Compute:

   • Google Cloud Platform (GCP)

   • Google Colab

   • Kaggle Notebooks