Do you feel intimidated when people use the words "Machine Learning"? While learning algorithms can be complex, quite often the basic ideas are much simpler.
I'll give an introduction to classification, a major application of "Machine Learning". The goal is to automate the labeling of documents based on anything that appears inside them (words, numbers, titles, html tags, whatever). Along the way, we'll talk about the difference between supervised and unsupervised learning and we'll cover the basic ideas behind a few different classification algorithms.
The course is meant to be completely introductory and we will start from first principles (including a little bit of math - basic, I promise). We'll discuss methods like decision trees, and clustering and then go into a little more depth on the Naive Bayes algorithm, which we will implement.
Note: All proceeds will be donated to the Memorial Sloan-Kettering Cancer Center. Snacks and Drinks will be provided!
Taught by Matt DeLand
Data Scientist at Groupon
I was the lead data scientist at Hyperpublic, a data platform for rich local data. Soon, I will be living in California and working as a data scientist at Groupon. Before Hyperpublic, I received my PhD from Columbia in math and worked as an assistant professor at the University of Michigan.