When I generate a Matlab function of a neural network, it comes with the normalization/re-normalization constants. Will these constants affect the neural network performance on another data set? Why?
2 vues (au cours des 30 derniers jours)
Afficher commentaires plus anciens
Anderson
le 14 Nov 2015
Réponse apportée : Greg Heath
le 15 Nov 2015
The normalization/re-normalization (for example, mapping the data to [-1,1] or [0,1]) is built for the training data. What does make the normalization constants work to another data set? And if the new data have large values than the training data?
0 commentaires
Réponse acceptée
Greg Heath
le 15 Nov 2015
Not if both datasets have similar summary statistics (e.g., mean/std for mapstd or min/max for mapminmax).
That is why sometimes it is better to explicitly normalize before training and explicitly denormalize after training.
Hope this helps.
Thank you for formally accepting my answer
Gregg
0 commentaires
Plus de réponses (0)
Voir également
Catégories
En savoir plus sur Deep Learning Toolbox dans Help Center et File Exchange
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!