Problem Motivation
- Problem common sighted in unsupervised learning as well as supervised learning
Advice for Applying PCA
- We know by now that PCA can reduce the data while representing original data, thus making faster learning algorithm.
Reconstruction from compressed representation
- PCA compression thousand into hundred dimensional features
Choosing the Number of Principal Components
- n dimensional features in large data scale usually have arround thousand number that most of them are highly correlated
Principal Component Analysis Algorithm
- PCA to reduce dimension data
Principal Component Analysis problem formulation
- PCA the most popular for DR
Motivation II : Data Visualization
- Last: DR for compressing data
Motivation I : Data Compression
- Useful for reduce the computation and less data input making faster process for learning algorithm
K-means algorithm
- Clustering Algorithm is used to classify the data structure that not labeled at the beginning.
Unsupervised Learning: Introduction
- First Unsupervised Learning algorithm that learn from unclassified data