Practice Common Activation Functions - 7.2.2 | 7. Deep Learning & Neural Networks | Advance Machine Learning
K12 Students

Academics

AI-Powered learning for Grades 8–12, aligned with major Indian and international curricula.

Academics
Professionals

Professional Courses

Industry-relevant training in Business, Technology, and Design to help professionals and graduates upskill for real-world careers.

Professional Courses
Games

Interactive Games

Fun, engaging games to boost memory, math fluency, typing speed, and English skillsβ€”perfect for learners of all ages.

games

7.2.2 - Common Activation Functions

Learning

Practice Questions

Test your understanding with targeted questions related to the topic.

Question 1

Easy

What is the output range of the Sigmoid function?

πŸ’‘ Hint: Think about what a probability represents.

Question 2

Easy

Which activation function is known to output values between -1 and 1?

πŸ’‘ Hint: Consider functions that also help with zero-centering.

Practice 4 more questions and get performance evaluation

Interactive Quizzes

Engage in quick quizzes to reinforce what you've learned and check your comprehension.

Question 1

What is the output range of the Sigmoid function?

  • 0 to 1
  • 0 to 100
  • Negative Infinity to Positive Infinity

πŸ’‘ Hint: Think about probabilities.

Question 2

True or False: The Tanh function can output values between 0 and 1.

  • True
  • False

πŸ’‘ Hint: Consider the definition of Tanh.

Solve 1 more question and get performance evaluation

Challenge Problems

Push your limits with challenges.

Question 1

You have a binary classification problem. Discuss the advantages and disadvantages of using Sigmoid versus Tanh as activation functions in your network.

πŸ’‘ Hint: Consider both the output ranges and the associated gradients.

Question 2

Explain how you would implement Leaky ReLU in a neural network and under which circumstances you would choose it over standard ReLU.

πŸ’‘ Hint: Think about the situations in your model where neurons might output zero.

Challenge and get performance evaluation