[coursera/ImprovingDL/week3]Hyperparameter tuning, Batch Normalization(summary&question)

The video for this week is easy.

3.1  hyperparameter tuning

try random

select a zone: log scale

model/parallel model: depend on the computation power

3.2 Batch Normalization

normalize the hidden units: z

3.3 multi-class classification

softmax regression

softmax classification

question:

WA: 8.Batch norm can be learned using Adam, Gradient descent with momentum, or RMSprop, not just with gradient descent.