quiz bu lëkkale ak tegtal · Diggante Niveau

Seetug architecture neuronal

Xoolaat barabi seetlu NAS, algorithm yi, njëgu seetlu bu teel, féexal DARTS, séddoo diisaay, ak jàngat caveats. Saytu xalaat yi ak yaatuwaayam.

Yooni njiit yu jëm ciSeetug arsitektu neuronal
Laaj 1 de 8

Lan mooy Seetug Architecture Neural?

Xoolaatal laaj bu nekk8 laaj

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

  1. Lan mooy Seetug Architecture Neural?
    • Defarum jumtukaayu reso neuronal bi
    • Etiketu done yiñ tàggat
    • Seddal serveur GPU yi
    • Bind dokimaa ngir model
  2. Yan ñatti mbir ñooy màndargaal anam NAS?
    • Done, optimisatër, ak bàyyi
    • Barab seetlu, pexem seetlu, ak xayma def
    • Enkodeur, dekodeer, ak bàyyi xel
    • Tàggat, saytu, ak ensemble test
  3. What accelerator scale did the original reinforcement-learning NAS paper report for its large search?
    • One GPU for every NAS method
    • A fixed cost of exactly 1,000 GPU-days for every search
    • An experiment using 800 GPUs in that study
    • No accelerator use during architecture search
  4. Ban pexe DARTS di jëfandikoo ngir gëna yombal seetlu bi?
    • Dafay tàggat ci benn misaal
    • Dina dindi bépp couche bu nëbbu
    • Seetug aleatër rek lay jëfandikoo
    • Dafay féexal tànneefi architecture yu wuute yi ci yeneen yu wéy yuñ mëna gëna xéewale ci degrade yi
  5. Luy 'supernet' ci NAS buy séddoo diisaay?
    • Benn reso bu bari ay parametre yu am architecture yiñ tànn yépp, ñu bokk seen diisaay
    • Reseau bu am ay miliyaar ciy parametre
    • Reseau buy dox ci kaw ordinatër yu mag kese
    • ab kopi bu model
  6. What did the HURRICANE hardware-aware NAS study evaluate?
    • One architecture that is guaranteed optimal on every device
    • Tailored architectures for three hardware types under matched latency constraints
    • A language model trained without any hardware measurements
    • A method that removes latency from architecture evaluation
  7. What is one limitation of weight-sharing NAS supernets?
    • They remove all architecture choices
    • They guarantee the globally best architecture
    • The shared weights can bias architecture rankings relative to training each candidate independently
    • They do not use neural networks
  8. What does a NAS evaluation need to report for a fair comparison?
    • Only the best test score
    • The GPU brand alone
    • The model name without settings
    • Search space, compute budget, validation protocol, and final retraining setup