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?
3 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Anderson
el 14 de Nov. de 2015
Respondida: Greg Heath
el 15 de Nov. de 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 comentarios
Respuesta aceptada
Greg Heath
el 15 de Nov. de 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 comentarios
Más respuestas (0)
Ver también
Categorías
Más información sobre Deep Learning Toolbox en Help Center y File Exchange.
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!