Practice Activation Functions (8.1.2) - Deep Learning and Neural Networks

Practise this section

10 questions

Flashcard drill
4 cards from this section. Quick, good the night before a test.
Exercise
6 questions · about 4 min · pass mark 70%. Hints available.
Sign up to start the exercise
Quiz
4 questions · about 3 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What does the Sigmoid activation function output range?
Show hintHide hint
Think of a logistic curve.
Question 2.
What is the formula for Tanh?
Show hintHide hint
It uses exponential functions.
3Question 3.
What is the output range of the Sigmoid function?
- (-1, 1)
- (0, 1)
- All real numbers
Show hintHide hint
Think about binary outcomes.
4Question 4.
The Softmax function is typically used for what kind of tasks?
- Regression
- Binary Classification
- Multi-Class Classification
Show hintHide hint
Recall its function in the context of classifying multiple categories.
Question 5.
Given a set of logits [1.2, 0.9, 0.4], calculate the Softmax probabilities.
Show hintHide hint
Remember to normalize the exponentials.
Question 6.
Explain how replacing ReLU with Leaky ReLU could be beneficial in a highly convoluted network.
Show hintHide hint
Think about neuron activation sustainability.

6 more questions in this section. Enroll free to practise them all.