machine learning introduction

Estimated reading time: 2 minutes

If you want to unlock supervised vs unsupervised machine learning, this is a place to stop off and review what you can learn more about expanding your data science knowledge.

In this video, you will be taken through the steps to decide on how to approach this, analyze your data through trial and error, which will give you a deep learning experience.

This area is split into two:

(A) Where the model is built around what the model builder wants, based on the input data they think are most appropriate, this can be commonly referred to as supervised machine learning.

(B) On the other hand unsupervised machine learning looks at the relationship between the data points, and how that relationship explains what that data or category or cluster of data is telling you.

The difference between the two looks to close the gap around regression problems, and also using the label data can sometimes not always tell the true story as the data points in the labeled data might not always showing the same pattern.

It will be a great building block if you want to go on and learn about classification, k-means, linear regression, or logistic regression. Some of the discussion talks about clustering and how that can influence the model you build.

Our supervised learning model section of the below video takes you through how you would look to identify if a set of data was suitable for a learning model, and what part iteration through the process, helps play in help building prediction into the future.