Supervised Machine Learning Methods

Name: Supervised Machine Learning Methods
Author: Gabriel Popoola

In this chapter you’ll learn about supervised learning concepts and techniques. It will cover linear and logistic regression. You will learn about support…

Preview the first lesson free — get full access to all 4 lessons.

Request a demo Sign in

Course: On-Demand

Welcome to Knowledge City's course on machine learning, supervised machine learning methods. In these lessons, you'll learn about linear and logistic regression, support vector machines, decision trees and random forest, and neural networks. This lesson will be on linear and logistic regression. During this lesson, you'll learn what is linear regression, what is logistic regression, how are linear and logistic regression used, and how are linear and logistic regression implemented? What is linear regression? Linear regression is one of the most basic machine learning algorithms used to predict a continuous variable. In simple linear regression, there is one independent variable used to predict the dependent variable. And in multiple linear regression, there are multiple dependent variables used to predict the dependent variable. Some uses include statistics, trend evaluation, and marketing effectiveness evaluation. What is logistic regression? Logistic regression is a very popular supervised machine learning technique that is typically used for classification problems. It uses multiple independent variables to predict a class by utilizing maximum likelihood estimation. Logistic regression is best used for binary classification problems, although it isn't completely restricted to this category of problems. Some uses include spam filters, identifying whether a tumor is benign or malignant, and predicting the likelihood of an event occurring. Now, we're gonna get into how linear and logistic regression are implemented in Python. So these implementations, we'll be using the scikit-learn package, which once again contains a wide variety of supervised and unsupervised machine learning, model and algorithm implementations. And it's a really good place to start if you're just getting into machine learning. So you can try out some of the more simple and basic models before diving into the more complex ones. So the linear regression is using the diabetes dataset. As you can see here, the mean absolute error for that is about 41, which means that on average, whenever a prediction is being made, the solution is about 41 points off. So this, of course, is bad, but in this case, it doesn't necessarily matter because the purpose of this is just to show how easy it is to implement a linear regression model. And you know, of course, there are datasets out there where the regression would perform a lot better. But this diabetes dataset is one of the more complex regression datasets. Next, we're gonna go on to logistic regression. This is using the breast cancer dataset. And as you can see here, the accuracy is about 94%, which is pretty good. Of course, there are classifiers that can perform significantly better, but 94% is definitely not a bad accuracy result, especially for such a simple and explainable machine learning model such as this. This concludes this lesson, and next up, we're going to discuss support vector machines. Thank you.

Beginner Provider : Gabriel Popoola 4 Lessons · 15m in Arabic, German, English, Spanish, French, Portuguese, Urdu, Chinese

Course Description

In this chapter you’ll learn about supervised learning concepts and techniques. It will cover linear and logistic regression. You will learn about support vector machines and their uses. This chapter also covers decision trees, random forests, ensemble learning and how they are all related. Neural networks are also discussed in this chapter.

What You'll Learn

Apply linear and logistic regression as supervised learning techniques
Use support vector machines and understand their uses
Build decision trees and random forests and how they relate
Explore ensemble learning and the benefits of ensembles over single basic classifiers
Understand neural networks within supervised machine learning

Key Takeaways

This chapter covers supervised learning concepts and techniques, including linear and logistic regression.
Support vector machines and their uses are discussed alongside decision trees and random forests.
The chapter explains decision trees, random forests, and ensemble learning and how they are all related.
It highlights the benefits of ensembles over single basic classifiers.
Neural networks are also discussed within the scope of supervised machine learning.

Frequently Asked Questions

What supervised machine learning techniques does this chapter cover?

It covers linear and logistic regression, support vector machines, decision trees, random forests, ensemble learning, and neural networks.

What will I learn about ensembles in this course?

You will learn about ensemble learning and the benefits of ensembles over single basic classifiers, and how decision trees, random forests, and ensemble learning all relate.

What skills does this course focus on?

It focuses on supervised learning, machine learning algorithms and methods, data mining methods, and decision tree learning.

Are neural networks included in this chapter?

Yes, neural networks are discussed in this chapter.