@berkansesen

Backpropagation Demystified: Neural Nets from First Principles

8h ago · 15 min read · Every modern deep learning framework — PyTorch, TensorFlow, JAX — does one thing brilliantly: it computes gradients for you. Call loss.backward() and millions of parameters update simultaneously. But

MCMC Island Hopping: An Intuitive Guide to the Metropolis-Hastings Algorithm

1d ago · 12 min read · Imagine you're a politician touring a chain of islands. Each island has a different population, and you want to spend time on each island in proportion to its population — more time on crowded islands

Hidden Markov Models: When Clusters Have Memory

2d ago · 15 min read · In the previous post, we clustered data into groups with K-Means and GMMs. Both methods assume observations are independent — each data point is analysed in isolation, with no regard for what came bef

From K-Means to GMM: Hard vs Soft Clustering

3d ago · 14 min read · You have a pile of unlabelled data and you want to find groups in it. K-Means is the algorithm everyone reaches for first — it's fast, simple, and usually works. But it makes a bold assumption: every

From MLE to Bayesian Inference: Why Your Estimate Needs a Prior

4d ago · 16 min read · In the MLE tutorial, we estimated a coin's bias by finding the single parameter value that maximises the likelihood. Flip a coin 3 times, get 3 heads, and MLE says \(\hat{\theta} = 1.0\) — the coin al