Machine Learning classes
| Andrew Ng’s Machine Learning (Stanford) | 2017 | ~9 weeks | Supervised/unsupervised learning | Octave, Scikit-learn | Outdated but covers foundational algorithms (e.g., k-means, SVM). |
| Deep Learning Specialization (Andrew Ng) | 2023 | ~5 months | Advanced DL architectures | TensorFlow | Covers CNNs, RNNs, and modern optimizers (Adam). |
| DeepMind’s Technical Writing (ML Basics) | 2021 | ~10 hrs | Writing for AI papers | LaTeX, Markdown | Useful for documenting algorithms (e.g., white papers). |
| Fast.ai: Practical Deep Learning | 2018 | ~3 weeks | Hands-on ML with real datasets | PyTorch | Best for quick deployment; emphasizes practicality over theory. |
| Google’s Machine Learning Crash Course | 2018 | ~5 hrs | Beginner ML workflows | TensorFlow | Good for quick basics but lacks depth. |
| MIT’s Introduction to Deep Learning | 2023 | ~4 weeks | PyTorch/TensorFlow fundamentals | PyTorch, TensorFlow | Updated for modern architectures (e.g., transformers). |
| Neural networks by 3Blue1Brown | 2025 | Great starter, best explanations. | |||
| Udacity’s Machine Learning Engineer Nanodegree | 2017 | ~3 months | Production-grade ML systems | TensorFlow, TFX | Covers MLOps (e.g., pipelines) but outdated for PyTorch. |
