Dear community,
In general, ANN models are non-identified. But, we attempt to address the identifiability problem by imposing some constraints. How can I impose these constraints using tf.keras.constraints?
Someone already did this?
Regards.
Dear community,
In general, ANN models are non-identified. But, we attempt to address the identifiability problem by imposing some constraints. How can I impose these constraints using tf.keras.constraints?
Someone already did this?
Regards.
If you are looking for how to just handle some constrains optimizzation you could take a look at:
Setting Fairness Goals with the TensorFlow Constrained Optimization Library