https://karthikvedula.com/Karthik's BlogKarthik S. Vedula's Blog -- Machine Learning, Coding Tutorials, Photos, and more! 2026-09-16T10:20:53-04:00 Karthik S. Vedula https://karthikvedula.com/ Jekyll © 2026 Karthik S. Vedula /assets/img/favicons/favicon.ico /assets/img/favicons/favicon-96x96.png An Explorable Guide to Protein Language Models2026-08-27T00:00:00-04:00 2026-09-16T10:16:24-04:00 https://karthikvedula.com/posts/protein-language-models/ Karthik S. Vedula Proteins fold, function, and evolve according to rules written into their amino acid sequence — and it turns out transformers are shockingly good at learning those rules. This post walks through how models like ESM, AlphaFold, and RFdiffusion actually work, from first principles up to the real architectures. This isn’t just a wall of text — nearly every section below has something you can clic... So how does PCA actually work?2025-08-25T00:00:00-04:00 2026-09-16T10:16:24-04:00 https://karthikvedula.com/posts/how-pca-works/ Karthik S. Vedula In the age of big data, making sense of high-dimensional datasets is a common challenge. Principal Component Analysis (PCA) is one of the most powerful tools in the data scientist’s toolkit for reducing dimensionality while preserving the essence of the data. By identifying directions—called principal components—along which the data varies the most, PCA allows us to simplify complex datasets, v... Thank you ML Club!2025-08-19T00:00:00-04:00 2025-08-19T14:57:09-04:00 https://karthikvedula.com/posts/thanks-ml-club/ Karthik S. Vedula “What I cannot create, I do not understand” — Richard Feynman. This post is long overdue, but better late than never! As I graduate high school and move on to college, I wanted to take a moment to wrap up this chapter of my ML journey. (For first-time visitors: I founded a Machine Learning Club at my high school, where I taught weekly lectures to over 60 students. This blog became the ho... ML Club Video (2024-25): Linear Regression to Neural Networks2025-07-11T00:00:00-04:00 2025-07-11T00:00:00-04:00 https://karthikvedula.com/posts/linear-to-nn/ Karthik S. Vedula Linear Regression is all about lines of best fit for a given dataset. But how do we find lines of best fit? Here is a quick answer: Start with a random line For each data point in dataset a) Find how “close” the line is to the point b) Depending on how close/far the line is, move the line a step towards the point Step 2 can be repeated multiple times (called epochs) I... The Algorithm Behind Ragas in Carnatic Music2024-11-25T00:00:00-05:00 2025-08-25T07:22:45-04:00 https://karthikvedula.com/posts/raga-interactive/ Karthik S. Vedula In Carnatic (and in Hindustani, though this blog post will focus on Carnatic) music, there is the concept of raga. At face value, a raga is just a scale or a collection of notes. Think of it as a subset of 16 possible notes: [R \subset {S, R1, R2, R3, G1, G2, G3, M1, M2, P, D1, D2, D3, N1, N2, N3}.] Each of these notes has a name, e.g. $S$ is Shadjam, and the numbers appended to the end of ...