Saved in:
| Main Author: | |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Online Access: | https://doi.org/10.5281/zenodo.18412250 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901608139325440 |
|---|---|
| author | abdelhannachi |
| author_facet | abdelhannachi |
| contents | <p>Readme</p> <p>The code computes archetypes of a data matrix X and provides r archetypes. The default value is r=4.</p> <p>The code requires essntially the data matrix X. X could be 2-dimensional, say nm, where n is the sample size, and m is the number of variables. It could also be 3-dimensional for example, nla*lo, for a field, in which n again is the sample size, and la is the latitudinal dimension and lo is the longitudinal dimension</p> <p>Example: [A B Za Zb] = aa_dynsys (randn(100,2));</p> <p>A and B are weight matrices Zb are the archetypes, Za are similar to archetypes but have smaller amplitudes (referred to in the ms as duals).</p> <p>In some cases the matrix may be scaled to get smoother convergence.</p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_18412250 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | abdelhannachi/hello_abdou: Archetypes via dynamical system abdelhannachi <p>Readme</p> <p>The code computes archetypes of a data matrix X and provides r archetypes. The default value is r=4.</p> <p>The code requires essntially the data matrix X. X could be 2-dimensional, say nm, where n is the sample size, and m is the number of variables. It could also be 3-dimensional for example, nla*lo, for a field, in which n again is the sample size, and la is the latitudinal dimension and lo is the longitudinal dimension</p> <p>Example: [A B Za Zb] = aa_dynsys (randn(100,2));</p> <p>A and B are weight matrices Zb are the archetypes, Za are similar to archetypes but have smaller amplitudes (referred to in the ms as duals).</p> <p>In some cases the matrix may be scaled to get smoother convergence.</p> |
| title | abdelhannachi/hello_abdou: Archetypes via dynamical system |
| url | https://doi.org/10.5281/zenodo.18412250 |