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
Complete sicp notes covering procedures and abstraction, data abstraction, modularity, metalinguistic abstraction, and interpreters. Full notes for MIT 6.001 Structure and Interpretation of Computer Programs by Abelson and Sussman.
Costin Gheorghe
Complete cs50 ai notes covering search algorithms, knowledge representation, uncertainty, optimization, machine learning, neural networks, and natural language processing. Full notes for Harvard's CS50 Introduction to AI with Python.
Costin Gheorghe
Complete cs231n notes covering image classification, convolutional networks, training deep networks, RNNs, attention, and generative models. The full CS231n study reference from the Stanford computer vision course.
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 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
CS230 lecture notes for Lecture 1 — Andrew Ng's complete introduction to deep learning, covering why deep learning now, the data-performance relationship, generative AI, and how CS230 differs from CS229.
Costin Gheorghe