Probability and Machine Learning

Ever wonder why probability shows up everywhere in machine learning?

It's not just background theory — it's what actually shapes the loss functions you train on every day. In this hour, we'll trace where those losses come from.
Why do we reach for mean squared error on a regression task, but cross-entropy on a classification task? Most of us learned these as rules to memorize. They're not. Both fall straight out of probability theory — once you ask "what distribution generated this data?", the right loss basically derives itself.

We'll walk through:

• How MSE emerges from a Gaussian likelihood
• Why this reframing makes the loss landscape feel principled instead of arbitrary

Come with basic ML familiarity and your questions — this is meant to be interactive, not a lecture. You'll leave seeing the losses you already use in a completely different light.

One hour. Bring a notebook.