Current Slide
Small screen detected. You are viewing the mobile version of SlideWiki. If you wish to edit slides you will need to use a larger device.
Model-Based Clustering
- A set C of k probabilistic clusters C1, …,Ck with probability density functions f1, …, fk, respectively, and their probabilities ω1, …, ωk.
- Probability of an object o generated by cluster Cj is
\[P(o|C_{j})=w_{j}f_{j}(o)\]
- Probability of o generated by the set of cluster C is
\[P(o|C)=\sum_{j=1}^{k}w_{j}f_{j}(o)\]
- Since objects are assumed to be generated independently, for a data set D = {o1, …, on}, we have,
\[P(D|C)=\prod_{i=1}^{n}P(o_{i}|C)=\prod_{i=1}^{n}\sum_{j=1}^{k}w_{j}f_{j}(o_{i})\]
- Task: Find a set C of k probabilistic clusters s.t. P(D|C) is maximized
- However, maximizing P(D|C) is often intractable since the probability density function of a cluster can take an arbitrarily complicated form
- To make it computationally feasible (as a compromise), assume the probability density functions being some parameterized distributions
Speaker notes:
Content Tools
Tools
Sources (0)
Tags (0)
Comments (0)
History
Usage
Questions (0)
Playlists (0)
Quality
Sources
There are currently no sources for this slide.