APPLICATION OF SUPERVISED LEARNING
DEEP LEARNING
|
Question
[CLICK ON ANY CHOICE TO KNOW THE RIGHT ANSWER]
|
|
|
Too many hidden layers
|
|
|
Hard to be implemented
|
|
|
Too complex
|
|
|
The convergence process is very slow
|
Detailed explanation-1: -Training speed: Batch gradient descent can be slow to converge when the training dataset is very large, as it uses the entire dataset to compute the gradient at each iteration. This can make training time-consuming and impractical in some cases.
Detailed explanation-2: -Stochastic gradient descent (SGD or “on-line") typically reaches convergence much faster than batch (or “standard") gradient descent since it updates weight more frequently.
Detailed explanation-3: -Sometimes a stable error gradient can lead to a local minima and unlike stochastic gradient descent no noisy steps are there to help get out of the local minima. The entire training set can be too large to process in the memory due to which additional memory might be needed. More items •06-Jan-2019