From the course: Amazon Web Services Machine Learning Essential Training

Unlock the full course today

Join today to access over 22,400 courses taught by industry experts or purchase this course individually.

Which algorithm should I use?

Which algorithm should I use? - Amazon Web Services (AWS) Tutorial

From the course: Amazon Web Services Machine Learning Essential Training

Start my 1-month free trial

Which algorithm should I use?

- [Instructor] After you've defined your business problem, and decided that it's a match for machine learning technologies, checked your data to make sure that it was clean and understandable, the next difficult challenge in working with machine learning is to determine which algorithm or, more properly, algorithms should I use? So to get us started, I've categorized the types of algorithms into two broad categories, supervised and unsupervised. And I've shown a couple of categories and examples of common algorithms. There are many, many more but this just kind of gets us started on this path. So in the supervised area, we commonly work with algorithms that do classification or regression. Classification results in a prediction as to whether a piece of data has membership in a class or a group. The most common business situation of this, or example, is categorizing photos. It's often of, is it a dog or is it a cat. That's sort of the Hello World of machine learning. An example…

Contents