Guide-yakabatana mibvunzo · Pakati Nhanho

Neural Architecture Search Quiz

Review NAS search spaces, algorithms, early search cost, DARTS relaxation, weight sharing, and evaluation caveats. Check assumptions and scope.

Nzira dzekutungamira dzinoenderanaNeural Architecture Search
Mubvunzo 1 ye 8

Chii chinoitwa neNeural Architecture Search otomatiki?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Chii chinoitwa neNeural Architecture Search otomatiki?
    • Dhizaini yechimiro cheneural network
    • Kuisa mazita ekudzidziswa data
    • Kutonhodza maseva eGPU
    • Zvinyorwa zvekunyora zvemhando
  2. Ndezvipi zvikamu zvitatu zvinotsanangura nzira yeNAS?
    • Dataset, optimizer, uye kudonha
    • Tsvaga nzvimbo, nzira yekutsvaga, uye fungidziro yekuita
    • Encoder, decoder, uye kutarisa
    • Kudzidzira, kusimbisa, uye bvunzo seti
  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. Ndeapi manomano akakosha anoshandiswa neDARTS kuita kuti kutsvaga kubudirire?
    • Inodzidzisa pane imwe muenzaniso
    • Inobvisa zvidimbu zvose zvakavanzika
    • Inoshandisa kutsvaga zvisina tsarukano
    • Iyo inodzoreredza discrete zvivakwa sarudzo mune inoenderera inogadziriswa nema gradients
  5. Chii chinonzi 'supernet' mukugovanisa uremu NAS?
    • Imwe pamusoro-parameterized network ine ese evamiriri ezvivakwa, ane huremu hwakagovaniswa
    • Network ine mabhiriyoni emaparamita
    • Network inoshanda pamakomputa makuru chete
    • Ikopi yekuchengetedza yemuenzaniso
  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