On a past personal project to learn about ML, I'd been struggling with implementing multiple variable gradient descent, and decided to write up a conceptual explanation of the method to make sure I had my head wrapped around it well enough. I referenced several sources for information about gradient descent, but most heavily influential was Andrew Ng's Supervised Machine Learning course on Coursera.

**carloscg**

# Stats Related Posts

## An Introduction to Gradient Descent

## An Introduction to (some) Bayesian Statistics

As part of my work at MIT, I needed to have a very good understanding of Bayesian statistics, which I have not had much exposure to before. For that reason, I wrote up this document going over some introductory facets of Bayesian statistics. It's very incomplete, of course, but it's a useful tool for brushing up. Here, I am walking through Kruschke's "Doing Bayesian Data Analysis." These are more my notes on the topic than any original lessons.

## Linear Regression and Gradient Descent Applied to NBA Data

A while back I wanted to gain some experience with ML, so I started off with a very simple application of linear regression to NBA data, detailed here.