Week 4: Supervised and Unsupervised Learning

Week 4: Supervised and Unsupervised Learning

Announcements

Class participation, EdSTEM, Figma, and Google Folder.
(Back to Course Index Page)

Tuesday

Supervised learning

From Algorithms perspective
From Dataset perspective

Unsupervised learning

From Algorithms perspective
From Dataset perspective
Clustering
Dimmension Reduction

Clustering

Overview
K-means
DBSCAN

Dimmension Reduction

Decomposing signals in components
Principal component analysis (PCA)
Kernel Principal Component Analysis (kPCA)
Independent component analysis (ICA)

Datasets

Popular datasets, UCI Datasets
Other institutions also use these datasets.
More datasets from CMU Statistics & Data Science
Google Open Datasets
Microsoft Research Open Datasets
sklearn datasets examples
sklearn Datasets User Guide
7.1. Toy datasets
38 Examples using the iris dataset (classification and clustering)
14 examples using the diabetes dataset (regression)

The Diabetes dataset

Regression
Efron, Bradley, Trevor Hastie, Iain Johnstone, and Robert Tibshirani. "Least angle regression." The Annals of statistics 32, no. 2 (2004): 407-499.
Cited by 11138
Google Scholar has the Paper PDF file
lab 04

Read accepted posters

AAAI Three Years

Thursday

Midterm

Research questions
Literature review
Paper format, two-page poster and full length eight-page paper
Timeline
Team, student pairs

Math

textbooks
Applied Math and Machine Learning Basics
Math4ML from CS 189A at UC Berkeley

Concept

Loss function
Accuracy
Train-test
Cross validation
Overfitting and underfitting

Textbooks

All textbooks are free available online, and are optinal, not required.

Deep Learning by Ian Goodfellow, Yoshua Bengio, and Aaron Courville
Table of Contents
Machine Learning Basics
A Course in Machine Learning by Hal Daume III
Unsupervised Learning
Machine Learning by Tom Mitchell

Other courses

From Week 02 notes
Teach like a DJ
Computers and Education
The flipped classroom: A review of its advantages and challenges, the PDF file