From the course: Machine Learning and AI Foundations: Clustering and Association

Unlock the full course today

Join today to access over 24,800 courses taught by industry experts.

Methods for measuring distance

Methods for measuring distance

From the course: Machine Learning and AI Foundations: Clustering and Association

Start my 1-month free trial Buy for my team

Methods for measuring distance

“

- [Instructor] I want to pause for a moment to zero in on a topic briefly, but I think it's an important one. I basically want to make the case that hierarchical is not dead, or at least shouldn't be. It is an older technique, it doesn't scale very well, but we've learned some useful things from the dendrogram. I also want to point out that there's something unique to hierarchical, a benefit that you don't really get anywhere else. So let's revisit the hierarchical menu. And this technique has been around for a long, long time, so you're going to be able to find hierarchical in whatever your tool of choice might be. Let's go to method, and this is really what makes hierarchical unique is the wealth of different options that you have here. And I really think that due diligence requires that you consider more than these. So the first time I was on a big cluster analysis project was many years ago. I was still in my 20s, I was just starting out doing consulting work, and I had a dataset…

Contents