CNN Pooling and Activation Functions 3

Question 1

What distinguishes the ELU (Exponential Linear Unit) activation from ReLU?

Accepted Answer

ELU outputs negative values for negative inputs using an exponential, giving non-zero mean activations

Answer

ELU uses an exponential decay for negative inputs, pushing mean activations closer to zero and speeding up learning compared to ReLU.

Question 2

In the context of pooling, what does 'stride' control?

Accepted Answer

How much the pooling window moves at each step across the feature map

Answer

Stride determines the step size of the pooling window as it slides across the feature map, controlling output size and overlap.

Question 3

Which activation function outputs values strictly between 0 and 1 and is commonly used for binary classification output layers?

Accepted Answer

Sigmoid

Answer

Sigmoid maps any real-valued input to the (0, 1) range, making it suitable for binary classification where outputs represent probabilities.

Question 4

What is fractional max pooling?

Accepted Answer

Max pooling with a non-integer kernel size or stride, producing irregular output dimensions

Answer

Fractional max pooling uses random or pseudo-random pooling regions with non-integer reduction ratios, acting as a form of data augmentation.

Question 5

How does the Softmax activation function differ from Sigmoid when used in output layers?

Accepted Answer

Softmax outputs sum to 1 across all classes, while Sigmoid outputs each class independently

Answer

Softmax normalizes outputs so they form a probability distribution summing to 1, making it ideal for mutually exclusive multi-class classification.

CNN - Convolutional Neural Networks Practice Test