Hi,
In trainData a weight per sample can be defined in create method. Weights are used in backprop, rprop method.
When you call calcError weigths are not used.
I think that calcError must use sample weight to give a good error value. Am I wrong?
1 | initial version |
Hi,
In trainData a weight per sample can be defined in create method. Weights are used in backprop, rprop method.
When you call calcError weigths are not used.
I think that calcError must use sample weight to give a good error value. Am I wrong?
Hi,
In trainData a weight per sample can be defined in create method. Weights are used in backprop, rprop method.
When you call calcError weigths are not used.
I think that calcError must use sample weight to give a good error value. Am I wrong?
Hi,
In trainData a weight per sample can be defined in create method. Sample Weights are used in backprop, rprop method.
When you call calcError sample weigths are not used.
I think that calcError must use sample weight weights to give a good error value. Am I wrong?