Content deleted Content added
added a 3D visualization of K-means with k = 3, made from a publicly available dataset (cited within caption) |
Citation bot (talk | contribs) Add: publisher, arxiv, doi, pages, issue, volume. | Use this bot. Report bugs. | Suggested by Dominic3203 | Linked from User:LinguisticMystic/cs/outline | #UCB_webform_linked 1079/2277 |
||
| (One intermediate revision by one other user not shown) | |||
Line 63:
</ref>
==The
The most intuitive nearest neighbour type classifier is the one nearest neighbour classifier that assigns a point {{mvar|x}} to the class of its closest neighbour in the feature space, that is <math>C_n^{1nn}(x) = Y_{(1)}</math>.
Line 107:
| url = https://archive.org/details/arxiv-1202.2194
| journal = International Journal of Remote Sensing
| volume = 32
}}</ref>▼
| issue = 21
| pages = 6109–6132
| doi = 10.1080/01431161.2010.507795
| arxiv = 1202.2194
▲ }}</ref>
The naive version of the algorithm is easy to implement by computing the distances from the test example to all stored examples, but it is computationally intensive for large training sets. Using an approximate [[nearest neighbor search]] algorithm makes ''k-''NN computationally tractable even for large data sets. Many nearest neighbor search algorithms have been proposed over the years; these generally seek to reduce the number of distance evaluations actually performed.
Line 233 ⟶ 238:
==Further reading==
* {{cite book |editor=Dasarathy, Belur V. |editor-link=Belur V. Dasarathy |year=1991 |title=Nearest Neighbor (NN) Norms: NN Pattern Classification Techniques |publisher=IEEE Computer Society Press |isbn=978-0818689307}}
* {{cite book |title=Nearest-Neighbor Methods in Learning and Vision |editor=Shakhnarovich, Gregory |editor2=Darrell, Trevor |editor3=Indyk, Piotr |publisher=[[MIT Press]] |year=2005 |isbn=978-0262195478}}
| |||