Gids-gekoppelde quiz · Middelmatig Niveau

Loterij Ticket Hypothese Quiz

Controleer uw kennis van loten, initialisatie, snoeien en de grenzen van claims over schaarse neurale netwerken.

Gerelateerde gidspadenHypothese van loterijbiljetten
Vraag 1 van 8

Wat is een 'winnend ticket' in deze hypothese?

Bekijk elke vraag8 vragen

Antwoorden en uitleg verschijnen terwijl je de quiz doet.

  1. Wat is een 'winnend ticket' in deze hypothese?
    • Een schaars subnetwerk dat, getraind vanaf de oorspronkelijke init, overeenkomt met het volledige netwerk
    • Een netwerk met meer parameters dan normaal
    • Een voorgetraind model gedownload van internet
    • Een willekeurig geraden reeks hyperparameters
  2. In the original lottery-ticket experiments, what was paired with the discovered sparse mask when retraining a ticket?
    • Fresh random values for every surviving weight
    • The surviving weights’ matched original initialization
    • A different architecture for each pruning round
    • The final trained weights with no resetting
  3. Wie heeft de loterijhypothese voorgesteld?
    • Goede kerel (2014)
    • Krizjevski, Sutskever, Hinton (2012)
    • Frank en Carbin (2018)
    • Zilver en collega's (2016)
  4. Which procedure did the original Lottery Ticket Hypothesis paper use to identify winning tickets?
    • Randomly remove a fixed half of all weights once
    • Iterative magnitude pruning with a reset to the original initialization
    • Add dropout after each pruning round
    • Increase the learning rate after every epoch
  5. How should the idea that overparameterization helps optimization find a trainable sparse structure be described?
    • A conjecture or proposed explanation, not a result established by the original experiments
    • A theorem proven for every neural-network architecture
    • A guarantee that all weights can be removed without loss
    • A claim that pruning eliminates the need for training data
  6. What does a strong lottery-ticket result claim in its theoretical setting?
    • Every randomly initialized network already solves any task
    • A sufficiently overparameterized randomly initialized network can contain a pruned subnetwork that approximates a target without further weight training
    • Pruning always preserves the trained model’s accuracy
    • A sparse network never needs data
  7. What does iterative magnitude pruning remove at each pruning step?
    • The training examples with the lowest labels
    • The neurons with the most outgoing connections
    • Weights with the smallest magnitudes
    • All weights in the final layer
  8. Which datasets were used in the original paper’s reported lottery-ticket experiments?
    • ImageNet and COCO only
    • LibriSpeech and Common Voice
    • SQuAD and GLUE
    • MNIST and CIFAR-10