DR+Clustering
From ResearchWiki
m |
m |
||
| Line 1: | Line 1: | ||
| - | == | + | === CS 6150: Graduate Algorithms Project === |
| - | + | ||
'''High dimensions are "weird"'''. | '''High dimensions are "weird"'''. | ||
| - | ''A mathematician and his best friend, an engineer, attend a public lecture on geometry in thirteen-dimensional space. | + | ''A mathematician and his best friend, an engineer, attend a public lecture on geometry in thirteen-dimensional space.'' |
| - | "How did you like it?" the mathematician wants to know after the talk. | + | ''"How did you like it?" the mathematician wants to know after the talk. '' |
| - | "My head's spinning", the engineer confesses. "How can you develop any intuition for thirteen-dimensional space?" | + | ''"My head's spinning", the engineer confesses. "How can you develop any intuition for thirteen-dimensional space?" '' |
| - | "Well, it's not even difficult. All I do is visualize the situation in arbitrary N-dimensional space and then set N = 13."'' | + | ''"Well, it's not even difficult. All I do is visualize the situation in arbitrary N-dimensional space and then set N = 13."'' |
| - | And Clustering is "hard" | + | '''And Clustering is "hard"''' |
| + | Athough Amit Daniely, Nati Linial, Michael Saks say its only hard when it does not matter!) | ||
| + | |||
| + | ==Goal== | ||
| + | Understand the impact of dimensionality reduction methods on clustering. Try to uncover relationship between a dimensionality reduction method and a clustering technique of your choice (if there exists any). | ||
==Data== | ==Data== | ||
Revision as of 06:28, 5 October 2012
Contents |
CS 6150: Graduate Algorithms Project
High dimensions are "weird".
A mathematician and his best friend, an engineer, attend a public lecture on geometry in thirteen-dimensional space.
"How did you like it?" the mathematician wants to know after the talk.
"My head's spinning", the engineer confesses. "How can you develop any intuition for thirteen-dimensional space?"
"Well, it's not even difficult. All I do is visualize the situation in arbitrary N-dimensional space and then set N = 13."
And Clustering is "hard"
Athough Amit Daniely, Nati Linial, Michael Saks say its only hard when it does not matter!)
Goal
Understand the impact of dimensionality reduction methods on clustering. Try to uncover relationship between a dimensionality reduction method and a clustering technique of your choice (if there exists any).
Data
MNIST Digits data:
Leader Board
| Data | # Data points | # Dimensions | # Target Dimensions | Dimensionality Reduction Method | Clustering Technique | Rand Index | NMI | Accuracy |
|---|---|---|---|---|---|---|---|---|
| MNIST | ||||||||
| Gisette | ||||||||
| Olivetti Faces |
