Exploring “Linear” in Linear Regression
Linear regression is one of those things you learn early, use forever, and never quite slow down to inspect. So here’s a slow inspection — three questions that look obvious until you actually try to answer them. The first two are warm-ups. The…
Read More[C1] What Machines Actually Do (And What They Don’t)
Every time you use Google Maps at 5:30 PM, something remarkable happens — and it has nothing to do with intelligence. The app doesn’t “know” traffic the way a local cabbie knows the city. It has no mental map, no concept of rush hour,…
Read More[ML 1.a] ML Foundations – Linear Combinations to Logistic Regression
Every machine learning model — from simple house price predictors to neural networks with billions of parameters — starts with the same fundamental building block: the linear combination. Take some inputs, multiply each by a weight, and add them up.…
Read More[ML 1.b] Teaching AI Models: Gradient Descent
In the last post, we established the big idea: machine learning is about finding patterns from data instead of writing rules by hand. But we skipped a critical question — how does the machine actually find the patterns? When someone says “we…
Read More[ML 2] Making Sense Of Embeddings
When you search on Amazon for “running shoes,” the system doesn’t just look for those exact words – it also shows you “jogging sneakers,” “athletic footwear,” and “marathon trainers.” When…
Read More[ML 2.a] Word2Vec: Start of Dense Embeddings
When you type a search query into Google or ask Spotify to find “chill acoustic covers,” the system doesn’t just look for those exact letters. It understands that “chill” is related to “relaxing” and…
Read More[ML 2.b] Measuring Meaning: Cosine Similarity
In the previous posts, we established that embeddings turn everything into points in space and that Word2Vec showed how to learn those points from context. But we glossed over something critical: how do you actually measure “closeness”? When…
Read More[ML 2.c] Needle in the Haystack: Embedding Training and Context Rot
You’ve probably experienced this: you paste a 50-page document into ChatGPT or Claude, ask a specific question about something buried on page 37, and the model either ignores it, gives a vague answer, or confidently cites something from page 2…
Read More[MI 3] Seq2Seq Models: Basics behind LLMs
When you use Google Translate to turn a complex English sentence into Spanish, or when you ask Gemini to summarize a long email, the computer isn’t just looking at individual words. It’s following a path. It’s remembering where the sentence started…
Read More[MU 1] Advertising in the Age of AI
When you search for a product today, ads quietly shape what you notice. When you scroll Instagram, ads compete for slices of your attention. For decades, advertising has existed because humans have a simple limitation: we cannot evaluate everything. This…
Read More