EMERGING TRENDS IN COMPUTING
ARTIFICIAL INTELLIGENCE AND MACHINE LEARNING
|
Question
[CLICK ON ANY CHOICE TO KNOW THE RIGHT ANSWER]
|
Suppose we have a 5-layer neural network which takes 3 hours to train on a GPU with 4GB VRAM. At test time, it takes 2 seconds for single data point.Now we change the architecture such that we add dropout after 2nd and 4th layer with rates 0.2 and 0.3 respectively.What would be the testing time for this new architecture?
|
|
Less than 2 secs
|
|
|
Exactly 2 secs
|
|
|
Greater than 2 secs
|
|
|
Can’t Say
|
Explanation:
Detailed explanation-1: -Training a neural network often takes a substantial amount of time. For example, training EfficientNet B0 takes about 550 GPU hours on NVIDIA Ti2080. Because we don’t want to waste training time, it’s common practice to examine the model’s accuracy mid-training.
Detailed explanation-2: -Tune the Layers The number of layers can be tuned using the “for loop” iteration. This demonstration tune the number of layers two times. Each time, the number of layers is tuned between 1 to 3. Inserting regularization layers in a neural network can help prevent overfitting.
Detailed explanation-3: -Label smoothing is a general technique to speed up the training process of neural networks.
There is 1 question to complete.