Transfer Learning Quiz

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

Quiz covering Advanced Training

What you'll be asked

  1. What is the primary goal of transfer learning in machine learning?
  2. When fine-tuning a pre-trained model on a small target dataset, which strategy is most effective to prevent overfitting?
  3. In the context of transfer learning for Computer Vision, why are the initial layers of a Convolutional Neural Network (CNN) often 'frozen'?
  4. What is a common risk when 'fine-tuning' a pre-trained model with a learning rate that is too high?
  5. You are applying transfer learning by replacing the classification head of a model trained on ImageNet to classify specialized medical X-rays. If your new dataset is very similar to the original dataset in terms of domain, but very small, what is the best approach?

Answers and explanations come after you submit.