Model Training Quiz

5 questions Pass: 70% +25 pts (50 with Pro)

Quiz covering ML Development Lifecycle

What you'll be asked

  1. In the ML development lifecycle, what is the primary purpose of a validation dataset?
  2. You notice your model has high training accuracy but significantly lower validation accuracy. What is the most likely cause?
  3. Which of the following techniques is most effective for addressing a model that is underfitting?
  4. Why is it critical to shuffle your training data before starting the training process in stochastic gradient descent?
  5. During training, you observe that your loss function is oscillating wildly and failing to converge. Which hyperparameter adjustment is most likely to stabilize training?

Answers and explanations come after you submit.