Jàngale Taux Programming Quiz

Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.

1. Lan mooy njariñu wàllu 'warmup' ci kalendriye tolluwaayu jàng?
   • Tambali ci njëg bu ndaw ba noppi yokk, moytu ñàkka dal ci degrade yu teela am bruit
   • Ngir wàññi njubte gi mujj
   • Ngir teggi yenn done yu njëkk yi
   • ngir gelé poids yépp ci ndoorte li
2. Ban kalendriye mooy topp courbe demi-cosine bi wàcci dem ci njëg bi gëna ndaw?
   • Oràŋ bu sax
   • Cosinus
   • Oraire aleatoire
   • Yokkateg ligneer
3. Lan mooy xew sudee dañu yéeg lool ci ni ñuy jàngee?
   • Taggat yaram dafay boole ci saasi ak jaar yoon
   • Model bi dafay tàggat ndànk waaye saa yu nekk dafay am ndam
   • Perte bi mën na diverge wala osciller ci barabu wàññeeku
   • Dara soppeekuwul; njëg bi amul benn njariñ
4. Lan la step decay di def ci ni ñuy jàngee?
   • Yokk ko lineairement ci lote bu nekk
   • Dafay wéy di nekk
   • Dafa koy def ci jéego bu nekk
   • Dafa koy wàcce ci facteur fixe ci jamono yuñ tànn bu njëkk
5. What does a warm restart do to a learning-rate schedule?
   • It raises the learning rate again to begin another schedule cycle
   • It resets the model parameters to random values
   • It permanently fixes the learning rate at zero
   • It deletes the optimizer’s moment estimates
6. In Goyal et al.’s large-minibatch ImageNet setup, what did their warmup scheme address?
   • It removed the need for a validation set
   • It eased early optimization difficulties after the learning-rate scale increased with batch size
   • It changed the model architecture after each epoch
   • It converted the learning-rate curve into a cosine wave
7. In the cosine formula, what does T denote?
   • The number of model layers
   • Dayo lote bi
   • The schedule horizon or total number of steps used for the decay
   • The optimizer’s momentum coefficient
8. If the cosine schedule uses lr_min greater than zero, where does the rate approach at the end of the horizon?
   • Exactly zero regardless of lr_min
   • The original warmup starting rate
   • An unbounded value
   • The specified minimum learning rate