Check nearby libraries
Buy this book
Learning in high dimensional spaces is computationally expensive because of the curse of dimensionality. Consequently, there is a critical need for methods that can produce good low dimensional representations of the raw data that preserve the significant structure in the data and suppress noise. This can be achieved by an autoencoder network consisting of a recognition network that converts high-dimensional data into low-dimensional codes and a generative network that reconstructs the high dimensional data from its low dimensional codes.Experiments with images of digits and images of faces show that the performance of an autoencoder network can sometimes be improved by using a non-parametric dimensionality reduction method, Stochastic Neighbour Embedding, to regularize the low-dimensional codes in a way that discourages very similar data vectors from having very different codes.
Check nearby libraries
Buy this book
Showing 2 featured editions. View all 2 editions?
Edition | Availability |
---|---|
1
A non-linear dimensionality reduction method for improving nearest neighbour classification.
2005
in English
0494021748 9780494021743
|
aaaa
Libraries near you:
WorldCat
|
2
A non-linear dimensionality reduction method for improving nearest neighbour classification.
2005
in English
0494021748 9780494021743
|
zzzz
Libraries near you:
WorldCat
|
Book Details
Edition Notes
Thesis (M.Sc.)--University of Toronto, 2005.
Electronic version licensed for access by U. of T. users.
Source: Masters Abstracts International, Volume: 44-01, page: 0400.
GERSTEIN MICROTEXT copy on microfiche (1 microfiche).
The Physical Object
ID Numbers
Community Reviews (0)
Feedback?History
- Created October 26, 2008
- 2 revisions
Wikipedia citation
×CloseCopy and paste this code into your Wikipedia page. Need help?
December 15, 2009 | Edited by WorkBot | link works |
October 26, 2008 | Created by ImportBot | Imported from University of Toronto MARC record |