Practice Anatomy Of A Deep Neural Network (dnn) (1) - Deep Learning Architectures

Practice: Anatomy of a Deep Neural Network (DNN)

Lesson 1Deep Learning Architectures

Practise this section

8 questions

Flashcard drill
3 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
2 questions · about 1 min · pass mark 70%. Hints available.
Sign up to start the quiz

6 sample questions

Question 1.
What are the three main types of layers in a DNN?
Show hintHide hint
Think about the structure of a network.
Question 2.
Name one activation function used in DNNs.
Show hintHide hint
Think of functions that help add complexity.
3Question 3.
What are the three types of layers in a deep neural network?
- Input
- Output
- Hidden
- Input
- Classifier
- Output
- Input
- Output
- Feature
Show hintHide hint
Think about the basic structure of neural networks.
4Question 4.
True or False: A bias helps neurons to activate even when all inputs are zero.
- True
- False
Show hintHide hint
Consider how thresholds are set for activation.
Question 5.
Design a mini DNN architecture for classifying handwritten digits (0-9). Describe the layers, activation functions, and loss function you would use.
Show hintHide hint
Consider how many features you need to classify each digit.
Question 6.
Explain how the choice of activation function might influence a neural network's ability to learn complex patterns.
Show hintHide hint
Think about what happens if we only had linear activations.

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