שאלה | Suppose batch gradient descent in a deep network is taking excessively long to find a value of the parameters that achieves a small value for the cost function J(W[1],b[1],...,W[L],b[L]). Which of the following techniques could help find parameter values that attain a small value forJ? (Check all that apply)

Suppose batch gradient descent in a deep network is taking excessively long to find a value of the parameters that achieves a small value for the cost function J(W[1],b[1],...,W[L],b[L]). Which of the following techniques could help find parameter values that attain a small value forJ? (Check all that apply)

		Try using Adam
		Try better random initialization for the weights
		Try tuning the learning rate α
		Try mini-batch gradient descent
		Try initializing all the weights to zero

מיין לפי