NBD Lite #1: Intro to Supervised Learning
Learn the most popular ML use cases
Hey everyone!
from here.So, I was thinking of starting a daily shorter data learning series that only takes about 3 minutes (or less) for each post.💥
The series is called the NBD Lite series.
The aim is to provide concise yet practical knowledge to upskill you.
The content would vary from conceptual and technical to soft skills. From Data Science, Machine Learning, and Artificial Intelligence, we would cover them as well. For each post, I would also give recommendation material for more intense learning.✨
Don’t worry; I will keep posting longer articles for more in-depth learning.
Don’t miss the series! Subscribe for Non-Brand Data if you haven’t👇
Below is the table and visual representation of Supervised Learning!
In my professional and personal projects, supervised learning has been used constantly.
Many projects that come from business have certain areas of supervised learning to help solve their problem.
But do you know about supervised learning?
Definition and Goal
Supervised Learning is a machine learning model which we trained on a labeled dataset.
A labeled dataset means the training data consists of input and output labels. It usually takes the form of a table, as shown in the image below.
The dataset could be in many forms, but supervised learning aims to learn the representation pattern from the input features to predict the output label.
The model would predict the unseen data by mapping the features to the output.
Supervised Learning Types
Typically, there are two types of Supervised Learning: Classification and Regression.
Classification is supervised learning where the label to train and the output is a discrete class label. The model would try to separate the input features and assign them into certain categories based on the pattern.
An example of a use case is Fraud detection, where we predict someone is “Fraud” or “Not-Fraud.” There are only two classes from the model to predict.
Examples of Classification Machine Learning algorithms are:
In contrast, Regression is supervised learning in which the label to train is a continuous value, and the output is a real number. The model would predict a real number without a certain class.
For example, the model used to predict house price or item quantities is a regression use case.
Examples of Regression Machine Learning algorithms are:
That’s all for today! I hope this is helpful to you. In later posts, I will explain each supervised learning type in more detail.
Have you tried to utilize the supervised learning model in your projects? Let’s discuss it together!👇👇👇
FREE Material for your Supervised Learning❤️
Supervised Machine Learning Lecture Notes by Andreas Lindholm, Niklas Wahlström, Fredrik Lindsten, Thomas B. Schön.
ML For Beginners by Microsoft
See you next time!