Supervised Learning Essential Training

Course details

Data scientists and ML/AI students may need some practical experience with supervised learning algorithms. In this course, instructor Ayodele Odubela teaches you to apply models you’ve created to new data and to assess model performance. First, Ayodele outlines what supervised learning is and how to make predictions using labeled training data. She gives you an overview of the logistic regression algorithm, how to build a linear model in Python, and how to calculate model metrics. Next, Ayodele helps you create your first decision trees as well as k-nearest neighbors models using GridSearch. Ayodele covers how you can create artificial neural networks that are foundational for most deep learning work. She concludes with an ethical AI overview and asks you to consider the impact of your models.

Concepts

0. Introduction

01 - Supervised machine learning and the technology boom
02 - Using the exercise files
03 - What you should know

1. Supervised Learning with Python

04 - What is supervised learning
05 - Python supervised learning packages
06 - Predicting with supervised learning

2. Regression Modeling

07 - Defining logistic and linear regression
08 - Steps to prepare data for modeling
09 - Checking your dataset for assumptions
10 - Creating a linear regression model
11 - Creating a logistic regression model
12 - Evaluating regression model predictions

3. Decision Trees

13 - Identify common decision trees
14 - Splitting data and limiting decision tree depth
15 - How to build a decision tree
16 - Creating your first decision trees
17 - Analyzing decision tree performance
18 - Exploring how ensemble methods create strong learners

4. K-Nearest Neighbors

19 - Discovering your k-nearest neighbors
20 - What's the big deal about k
21 - How to assemble a KNN model
22 - Building your own KNN
23 - Deciphering KNN model metrics
24 - Searching for the best model

5. Neural Networks

25 - Biological vs. artificial neural networks
26 - Preprocessing data for modeling
27 - How neural networks find patterns in data
28 - Assembling your neural networks
29 - Comparing networks and selecting final models

Conclusion

30 - Ethical overview
31 - How can I keep developing my skills in supervised learning