Kvíz spojený s průvodcem · Střední úroveň
Hypotéza loterijního kvízu
Ověřte si, jak rozumíte loterijním losům, inicializaci, ořezávání a limitům tvrzení o řídkých neuronových sítích.
Otázka 1 z 8
Co je v této hypotéze „výherní tiket“?
Náhled každé otázky8 otázky
Odpovědi a vysvětlení se zobrazují, jak budete v kvízu.
- Co je v této hypotéze „výherní tiket“?
- Řídká podsíť, která, natrénovaná z původního init, odpovídá celé síti
- Síť s více parametry než obvykle
- Předtrénovaný model stažený z internetu
- Náhodně uhodnutý soubor hyperparametrů
- 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
- Kdo navrhl hypotézu loterijního lístku?
- Goodfellow (2014)
- Krizhevsky, Sutskever, Hinton (2012)
- Frankle a Carbin (2018)
- Stříbro a kolegové (2016)
- 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
- 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
- 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
- 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
- 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