The Wonderful World of Machine Learning

This is the home for the sessions content for the Fort Collins Data Science Meetup series on Machine Learning lead by Michael Szczepaniak

The first session, June 29, 2017

Sondra's ML overview, session 1.5, July 6, 2017

The second session, Linear Regression - Extreme Interpretability, July 13, 2017

The third session, Logistic Regression: Binary Classifier Workhorse, July 20, 2017

The fourth session, Linear & Quadratic Discriminant Analysis (LDA & QDA), July 27, 2017

The fifth session, Trees: There's Power in Numbers, August 24, 2017

The sixth session, Data Wrangling in R Part 1, January 10, 2018

The seventh session, Neural Networks from Scratch (Part 1 of 2)

Future session are tentatively schedule for:

• Date to be announced, session 8 - Neural Networks from Scratch (Part 2 of 2)
• Possible additional Neural Net sessions
• Date to be announced - Data Wrangling Part 2

Proposed Agenda

My goal for these sessions is for you to leave them with a good intuition for how the basic machine learning algorithms work and hopefully with a good enough start into how you might implement them yourself. Since most of us will spend a lot of time getting data into a form we can use, I've added a few modules on data wrangling.

To get the most out of these sessions, I recommend that you install Jupyter notebook and configure an R kernel in addition to the Python kernel that was installed with Jupyter. I'll be creating notebooks which use both R and Python code.

I'm going to try to work in concepts such as how to train models with boostrap methods like bagging, random forest and boosting as well as how the main cross-validation techniques work, but we may not have enough time to do much with these areas. Let me know your thoughts on how these sessions might be more beneficial to you.