Dear Xavier,


The reason you're seeing these results is that the default number of iterations (`n_iter`) is set low to allow for quick testing. Increasing the number of iterations improves accuracy. Each tutorial includes a comment next to the variable, providing guidance on the optimal number of iterations for better accuracy. This default setting is planned to be adjusted in the upcoming NEST release. 


All the best,

Agnes


On 2025-02-11 15:44, Xavier Otazu Porter wrote:
Hello,

I have downloaded several of the eprop python examples, and none of them generate the correct results. For example, the handwritten example, generates a rather random result (the red points data) that do not fit with the expected results. The sinus generation, also generates wrong results. If you want, I can send a small image (not did it now to avoid image spamming).


I am using NEST 3.8 with python 3.9 in a linux Rocks enviornment, and python 3.11 in a FreeBSD environment.

Thanks a lot in advance.

Xavier



Computer Vision Center
CONFIDENTIALITY WARNING


_______________________________________________
NEST Users mailing list -- users@nest-simulator.org
To unsubscribe send an email to users-leave@nest-simulator.org
-- 
Agnes Korcsak-Gorzo
Institute for Advanced Simulation (IAS-6)
Computational and Systems Neuroscience
Jülich Research Centre,
Jülich, Germany

https://www.fz-juelich.de/en/ias/ias-6

Forschungszentrum Juelich GmbH
52425 Juelich
Sitz der Gesellschaft: Juelich
Eingetragen im Handelsregister des Amtsgerichts Dueren Nr. HR B 3498
Vorsitzender des Aufsichtsrats: MinDir Stefan Müller
Geschäftsführung: Prof. Dr. Astrid Lambrecht (Vorsitzende),
Karsten Beneke (stellv. Vorsitzender), Prof. Dr. Ir. Pieter Jansens

Das Forschungszentrum Jülich stellt zurzeit auf einen neuen Zertifikatsanbieter zum digitalen Signieren von E-Mails um. Während dieser Umstellungsarbeiten kann es vorkommen, dass das DFN Community PKI Zertifikat, mit dem diese E-Mail signiert worden ist, als ungültig angezeigt wird.