Curriculum Learning Quiz

Answers and explanations appear as you take the quiz.

1. What ordering does a common curriculum-learning strategy use?
   • Present examples from easier to harder according to a chosen schedule
   • Always present the most difficult example first
   • Sort examples alphabetically and never change the order
   • Use only examples that already have perfect predictions
2. Who introduced the term 'curriculum learning' in a well-known 2009 paper?
   • Geoffrey Hinton
   • Yoshua Bengio and colleagues
   • Andrew Ng
   • Yann LeCun
3. In self-paced learning, who decides which examples count as 'easy' enough to train on early?
   • A human annotator labels difficulty by hand
   • The hardware scheduler
   • The model itself, based on which examples have low loss
   • A separate pre-trained difficulty classifier only
4. Why might curriculum learning help optimization?
   • It increases the learning rate automatically
   • It guarantees zero training error
   • It removes the need for a loss function
   • It smooths early objectives, helping avoid poor local minima
5. How should a team test whether an easy-to-hard curriculum helps a model?
   • Compare against a suitable baseline with the same data and compute budget
   • Assume it helps whenever the schedule has more stages
   • Measure training loss once and skip held-out evaluation
   • Compare runs that use different data and different compute
6. What is 'anti-curriculum' learning?
   • Training with no examples at all
   • Presenting harder examples before easier ones
   • Using only validation data
   • Disabling backpropagation
7. Which four tasks did the 2010 self-paced learning paper report in its experiments?
   • Speech translation, protein folding, weather prediction, and music synthesis
   • Image captioning, game playing, robotics, and medical diagnosis
   • Object localization, noun-phrase coreference, motif finding, and handwritten-digit recognition
   • Clustering, sentiment analysis, machine translation, and speech diarization
8. How can a curriculum be defined reproducibly?
   • Use the word “easy” without a criterion
   • Change the test set after each epoch
   • Select only examples the model already predicts correctly
   • Specify the example difficulty measure, ordering or schedule, and comparison baseline