Maswali yanayounganishwa na mwongozo · Ngumu Kiwango

Maswali ya AI ya makali

Tathmini makali ya AI kupitia kazi za ndani dhidi ya kijijini, rasilimali za kifaa, majaribio endelevu, ukaguzi wa mbano, mtiririko wa faragha, na mipango ya sasisho salama.

Njia za mwongozo zinazohusianaMakali ya AI
Swali 1 ya 8

Ni upelekaji upi ni mfano wa makali ya AI?

Hakiki kila swali8 maswali

Majibu na maelezo huonekana unapojibu maswali.

  1. Ni upelekaji upi ni mfano wa makali ya AI?
    • Processing close to where data is collected or used, such as a phone or local gateway
    • Training a model only on a central server
    • Using a larger model than the cloud
    • Disabling all connectivity
  2. Ni lazima programu ifanye kazi nje ya mtandao. Muundo wake unapaswa kujumuisha nini?
    • An assumption that every service is local
    • A useful failure mode for functions that still need remote retrieval
    • A larger model by default
    • A permanent network connection
  3. Kipengele cha ukingo kina GB 2 zinazopatikana, GB 1.2 za uzani, na GB 0.6 za bafa za muda. Ni nini kinachosalia kabla ya mahitaji mengine ya kipengele?
    • 0.8 GB, because only weights count
    • 1.4 GB, because weights use no runtime memory
    • 0.2 GB, leaving little margin for other needs
    • 2 GB, because buffers are outside the budget
  4. Alama fupi ya kifaa inaonekana nzuri. Je, inaweza kukosa nini?
    • Only the original model download time
    • Only the peak arithmetic rating
    • Only the model weight-file size
    • Thermal throttling and competition with other applications over time
  5. Baada ya kukadiria mfano ili kutoshea kifaa, ni nini kinapaswa kuangaliwa?
    • Only the new file size
    • Task performance on difficult inputs and intended environmental conditions
    • Whether the model loads once
    • A benchmark from another device
  6. A phone performs local inference but syncs logs to a server. What does this imply for privacy review?
    • Privacy review is unnecessary
    • Local inference means no data leaves the device
    • Logs and synchronization still need controls
    • The app is fully offline
  7. Why does the guide recommend versioning models?
    • To identify which model version ran on each device
    • To prevent all updates
    • To hide device resource use
    • To change the battery capacity
  8. What should an update plan include for intermittently connected devices?
    • Deleting the previous version before validation
    • A requirement that devices never reconnect
    • An unverified moving model
    • A safe update or rollback path