Week 4: Simple Classifiers¶

Topics¶

This week’s assignments will guide you through the following topics:

Simple classifiers: rectangular cuts, likelihood-based, SVM, fully connected neural networks, and boosted decision trees

Reading¶

Please read the following:

Sections 4.2 and 4.3 of [7]
Likelihood discriminant: [8]

Tasks¶

Complete the following tasks:

Run through the notebook: 04-simple-classifiers.ipynb
Modify it to train and evaluate a boosted decision tree. Hint.

Weekly Questions¶

Answer the following questions on Canvas:

How do the different types of classifiers differ: simple selection, likelihood-based, fully connected neural network, and boosted decision tree?
What are their pros and cons?

previous

Week 3 Notebook: Feature Engineering

next

Week 4 Notebook: Simple Classifiers