Intrinsic dimension estimation of data: an approach based on Grassberger-Procaccia's algorithm
| Type of publication: | Idiap-RR |
| Citation: | cam00IRR |
| Number: | Idiap-RR-33-2000 |
| Year: | 2000 |
| Institution: | IDIAP |
| Note: | To appear in Neural Processing Letters |
| Abstract: | In this paper the problem of estimating the intrinsic dimension of a data set is investigated. An approach based on the Grassberger-Procaccia's algorithm has been studied. Since this algorithm does not yield accurate measures in high-dimensional data sets, an empirical procedure has been developed. Grassberger-Procaccia's algorithm was tested on two different benchmarks and was compared to a TRN-based method. |
| Userfields: | ipdmembership={vision}, |
| Keywords: | |
| Projects |
Idiap |
| Authors | |
| Crossref by |
cam01art |
| Added by: | [UNK] |
| Total mark: | 0 |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
