This mid-level course takes you through how to create one of the most common types of machine learning: supervised learning models.
Overview
Syllabus
Introduction
- Supervised machine learning and the technology boom
- Using the exercise files
- What you should know
- What is supervised learning?
- Python supervised learning packages
- Predicting with supervised learning
- Defining logistic and linear regression
- Steps to prepare data for modeling
- Checking your dataset for assumptions
- Creating a linear regression model
- Creating a logistic regression model
- Evaluating regression model predictions
- Identify common decision trees
- Splitting data and limiting decision tree depth
- How to build a decision tree
- Creating your first decision trees
- Analyzing decision tree performance
- Exploring how ensemble methods create strong learners
- Discovering your k-nearest neighbors
- What's the big deal about k
- How to assemble a KNN model
- Building your own KNN
- Deciphering KNN model metrics
- Searching for the best model
- Biological vs. artificial neural networks
- Preprocessing data for modeling
- How neural networks find patterns in data
- Assembling your neural networks
- Comparing networks and selecting final models
- Ethical overview
- How can I keep developing my skills in supervised learning?
Taught by
Ayodele Odubela
