Unsupervised Machine Learning

Description

In this course, you will :

• Describe the types of problems that are suitable for Unsupervised Learning approaches.
• Explain the curse of dimensionality and how it makes clustering with many features difficult.
• Explain and apply common clustering and dimension-reduction algorithms.
• When appropriate, try clustering points and compare the performance of per-cluster models.
• Understand metrics relevant for characterising clusters.

Syllabus :

1. Introduction to Unsupervised Learning and K Means

• Introduction to Unsupervised Learning
• Introduction to Clustering
• K-Means
• K Means Notebook

 

2. Selecting a clustering algorithm

• Distance Metrics
• Curse of Dimensionality Notebook
• Hierarchical Agglomerative Clustering
• DBSCAN
• Mean Shift
• Comparing Algorithms
• Clustering Notebook

 

3. Dimensionality Reduction

• Dimensionality Reduction
• PCA Notebook 
• Dimensionality Reduction Notebook
• Non Negative Matrix Factorization
• Non Negative Matrix Factorization Notebook
• Dimensionality Reduction Imaging Example

Show more