Machine Learning Neural Networks 2

Question 1

What problem does batch normalization primarily solve in deep neural networks?

Accepted Answer

Internal covariate shift during training

Answer

Batch normalization addresses internal covariate shift by normalizing layer inputs, stabilizing and accelerating training.

Question 2

In a convolutional neural network, what does the stride parameter control?

Accepted Answer

How many pixels the filter moves per step

Answer

Stride determines how many pixels the convolutional filter shifts at each step, controlling the spatial dimensions of the output.

Question 3

Which technique randomly sets neuron outputs to zero during training to prevent overfitting?

Accepted Answer

Dropout

Answer

Dropout randomly deactivates a fraction of neurons during each training step, forcing the network to learn redundant representations.

Question 4

What is the vanishing gradient problem?

Accepted Answer

Gradients shrink exponentially as they propagate through many layers

Answer

In deep networks, gradients can become exponentially small during backpropagation, making it difficult to train early layers.

Question 5

What does the ReLU activation function return for a negative input value?

Accepted Answer

Zero

Answer

ReLU (Rectified Linear Unit) outputs zero for any negative input and passes positive values unchanged.

Machine Learning Practice Test