Machine Learning #2
Unsupervised Learning
Unsupervised Learning
In unsupervised learning, each data point in the dataset is not defined; the algorithm is given unlabeled data with the goal of finding a structure. when a structure is found in the dataset, they are put into clusters
Clustering Algorithm
Cluster analysis, or clustering, is an unsupervised learning task. It involves automatically discovering natural grouping in data.
Clustering algorithms interpret the input data and find natural groups or clusters in the feature space.
Applications of Unsupervised Learning
Google News: Google goes on the web and searches for hundreds of thousands of news articles and groups them into cohesive news stories.
Genomics(DNA Microarray Data): Given a group of different individuals, a clustering algorithm can be used to measure how much they do or do not have a certain gene, and create clusters based on the pattern.
Other Examples
Organizing computer clusters in a data center
Social Network Analysis
Market Segmentation
Astronomical Data Analysis
The Cocktail Party Problem
Two people are talking at a cocktail party, Let's assume there are two microphones somewhere in the room at different distances, if recordings are taken from the two microphones, a clustering algorithm can be used to separate each person’s voice from the recording.