com.thoughtworks.deeplearning.DifferentiableINDArray
If you write something like this:
implicit def optimizer: Optimizer = new LearningRate { def currentLearningRate() = 0.001 }
the learningRate will shared with all layers. If a Optimizer has state, then learningRate can NOT been shared.
If you write something like this:
the learningRate will shared with all layers. If a Optimizer has state, then learningRate can NOT been shared.