Activation Functions

Test your knowledge of activation functions, their characteristics, and their impact on training neural networks.

FREE QUIZ

10 Questions

~20 Minutes

Intermediate

Question 1

What is the primary role of an activation function in a neural network?

To reduce the dataset size To normalize input data To introduce non-linearity To connect hidden layers

Question 2

Which activation function outputs values strictly between 0 and 1?

ReLU Tanh Sigmoid Linear

Question 3

Which activation function is typically used for multi-class classification?

Sigmoid ReLU Softmax Linear

Question 4

Which function is known for turning all negative inputs into zero?

Tanh ReLU Softplus Sigmoid

Question 5

Which activation function has an output range of -1 to 1?

Tanh ReLU Sigmoid Softmax

Question 6

Which activation function is best suited for regression problems where output is unbounded?

Softmax Sigmoid Linear Tanh

Question 7

Which function is a smooth approximation of ReLU and always differentiable?

Softplus ReLU6 Hard Sigmoid Tanh

Question 8

Why is the ReLU function preferred in deep networks?

It is nonlinear and cheap to compute It compresses inputs to a narrow range It increases training time It guarantees smooth outputs

Question 9

Which activation function modifies the sigmoid curve for faster computation?

Softplus Hard Sigmoid ELU Tanh

Question 10

Which activation function is useful when you want to bound output to a maximum of 6?

ReLU6 ELU Tanh Sigmoid

0 / 10 Answered | 0:00