Neural Network non mutually exclusive cross entropy loss function
1 visualización (últimos 30 días)
Mostrar comentarios más antiguos
Manos Kav
el 4 de Mayo de 2018
Respondida: Greg Heath
el 5 de Mayo de 2018
Hello,
I have a neural network with 100 outputs which solves a binary classification problem, ie every output can take value 0 or 1. I want to use cross-entropy performance function but as I see it only supports classification with mutually exclusive outputs. Is there any way to use crossentropy for non mutually exclusive outputs? I have found this answer but it seems not to work. ( https://www.mathworks.com/matlabcentral/answers/213915-can-target-vector-of-neural-network-have-sum-of-columns-1 ) Thanks in advance.
0 comentarios
Respuesta aceptada
Greg Heath
el 5 de Mayo de 2018
The target matrix columns should contain the
NON-NEGATIVE UNIT SUM APRIORI CLASS PROBABILITIES !!!
See any text regarding statistical classification
Hope this helps
Thank you for formally accepting my answer
Greg
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!