Practice Activation Functions: Relu, Sigmoid, Tanh (1.2)

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 ReLU stand for?
Show hintHide hint
Think about the shape of its graph.
Question 2.
What range does the Sigmoid function output?
Show hintHide hint
Consider how it behaves at extreme inputs.
3Question 3.
What is the primary purpose of using activation functions in neural networks?
- To introduce linearity
- To introduce non-linearity
- To output probabilities
Show hintHide hint
Consider what happens if there are no activation functions.
4Question 4.
The output range of the Tanh function is:
- 0 to 1
- -1 to 1
- 0 to infinity
Show hintHide hint
Visualize their range on the graph.
Question 5.
Design a neural network architecture for a binary classification problem including how you would incorporate activation functions.
Show hintHide hint
Focus on the advantages of each activation function in context.
Question 6.
Investigate a scenario using Tanh in a specific type of network architecture and justify its advantages over using ReLU.
Show hintHide hint
Reflect on handling sequential data and its requirements.

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