7 articles
Complete CS229 lecture notes for the EM algorithm and Gaussian Mixture Models. Step-by-step derivation from Jensen's inequality to the E-step responsibilities and M-step closed-form updates, plus how EM relates to k-means and PCA.
Costin Gheorghe
A structured roadmap to learn machine learning youtube — from math prerequisites through deep learning. Best channels, video sequences, real projects, and the pitfalls that waste months.
Costin Gheorghe
Every topic in Stanford CS229, organized by lecture in one readable page: linear regression, GLMs, SVMs and kernels, neural networks, learning theory, k-means, EM, and reinforcement learning. A study reference to work through alongside the course, not a replacement for Andrew Ng's official PDFs.
Costin Gheorghe
Complete deeplearning.ai notes for Andrew Ng's Coursera Deep Learning Specialization — all 5 courses, neural networks, optimization, CNNs, sequence models, and NLP transformers, organized for studying.
Costin Gheorghe
Complete fast.ai notes for Jeremy Howard's Practical Deep Learning for Coders course — transfer learning, fine-tuning, CNNs, NLP, tabular data, and deployment, lesson by lesson.
Costin Gheorghe
Complete andrew ng machine learning notes covering every week of the Coursera ML specialization — linear regression through photo OCR, with key equations and practical takeaways.
Costin Gheorghe
Complete CS229 lecture notes for the SVM dual formulation. Step-by-step derivation from the primal margin problem to the dual using Lagrange multipliers and KKT conditions, plus why the dual form is what makes the kernel trick possible.
Costin Gheorghe