Practice Deep Neural Networks (dnns) (8.2) - Deep Learning and Neural Networks

Practice: Deep Neural Networks (DNNs)

Lesson 8.2Deep 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 defines a neural network as 'deep'?
Show hintHide hint
Think about how many layers separate the inputs from the outputs.
Question 2.
Name one common loss function used in regression tasks.
Show hintHide hint
Consider what function measures the average squared difference.
3Question 3.
What makes a neural network 'deep'?
- Having one hidden layer
- Having multiple hidden layers
- Having no hidden layers
Show hintHide hint
Consider the layers involved in processing the input.
4Question 4.
Is Mean Squared Error used for classification tasks?
- True
- False
Show hintHide hint
Think about the types of data being compared in classification.
Question 5.
Consider a DNN with multiple hidden layers. Discuss the potential trade-offs between having a very deep network versus a shallower one in terms of learning capacity and overfitting.
Show hintHide hint
Think about the relationship between complexity, performance, and risk of overfitting.
Question 6.
Design a basic neural network for classifying images. Indicate which loss function you would select and justify your choice.
Show hintHide hint
Consider what type of data you're working with and what function will best evaluate your model's performance.

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