Artificial Intelligence Foundations: Machine Learning

Course details

Machine learning is the most exciting branch of artificial intelligence. It allows systems to learn from data by identifying patterns and making decisions with little to no human intervention. In this course, you'll navigate the machine learning lifecycle by getting hands-on practice training your first machine learning model. Join instructor Kesha Williams as she explores widely adopted machine learning methods: supervised, unsupervised, and reinforcement. There's a focus on sourcing and preparing data and selecting the best learning algorithm for your project. After training a model, learn to evaluate model performance using standard metrics. Finally, Kesha shows you how to streamline the process by building a machine learning pipeline. If you’re looking to understand the machine learning lifecycle and the steps required to build systems, check out this course.

Concepts

0. Introduction

01 - Introduction to AI foundations - Machine learning course
02 - Reviewing the course scenarios

1. Understanding Machine Learning

03 - Exploring machine learning
04 - Examining how machines learn

2. Implementing a Machine Learning Solution

05 - Breaking down the machine learning lifecycle
06 - Framing machine learning problems
07 - Identifying a pre-built model
08 - Understanding tools used to train a model

3. Preparing Data for Machine Learning

09 - Obtaining data
10 - Visualizing and understanding data
11 - Understanding feature engineering
12 - Demo - Performing feature engineering

4. Training a Machine Learning Model

13 - Understanding learning algorithms and model training
14 - Exploring learning algorithms for classification
15 - Reviewing learning algorithms for regression
16 - Examining additional learning algorithms
17 - Training a custom machine learning model
18 - Demo - Training a custom machine learning model

5. Evaluating Model Performance

19 - Exploring common classification metrics
20 - Understanding the confusion matrix
21 - Exploring common regression metrics
22 - Determining feature importance
23 - Combating bias

6. Operationalizing a Machine Learning Pipeline

24 - Structuring a machine learning pipeline
25 - Demo - Designing and building a pipeline

Conclusion

26 - Your machine learning journey