Weight decay parameter and Jacobian matrix of a neural network
4 visualizaciones (últimos 30 días)
Mostrar comentarios más antiguos
Platon
el 19 de Feb. de 2014
Comentada: Greg Heath
el 21 de Feb. de 2014
I want calculate prediction intervals so I have 2 direct questions:
- How can I get the weight decay parameter 'alpha' (mse+alpha*msw) used when using 'trainbr' as a training algorithm?
- How can I get the neural network jacobian matrix (derivatives following weights) calculated during training?
0 comentarios
Respuesta aceptada
Greg Heath
el 19 de Feb. de 2014
Editada: Greg Heath
el 19 de Feb. de 2014
The documentation for trainbr is pretty bad.
help trainbr
doc trainbr
Look at the source code
type trainbr
I am not familiar with it but will take a look when I get time.
Meanwhile, if you make a run, the training record tr, contains 2 parameters
gamk: [1x31 double]
ssX: [1x31 double]
that are involved.
Hope this helps.
Thank you for formally accepting my answer
Greg
0 comentarios
Más respuestas (1)
Platon
el 21 de Feb. de 2014
1 comentario
Greg Heath
el 21 de Feb. de 2014
When using the obsolete msereg and mse with the regularization option, the weight parameters are alpha (specified error weight) and (1-alpha).
However when using trainbr, the weight parameters alpha and beta are calculated each epoch. Haven't decifered the logic yet. Might be faster to search the web.
Ver también
Categorías
Más información sobre Sequence and Numeric Feature Data Workflows 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!