Ikibazo gihuza ibibazo · Biroroshye Urwego

Moderi ya AI Yasobanuwe Ikibazo

Ikigereranyo cyicyitegererezo cyinjiza nibisohoka, wize ibipimo, hyperparameter, kugarura, guhuza neza, hamwe no guhitamo icyitegererezo ukoresheje icyitegererezo cyapimwe.

Inzira zijyanye no kuyoboraModeri ya AI
Ikibazo 1 Bya 8

Nibihe bigize porogaramu ya AI ni imashini yiga imashini ubwayo?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Nibihe bigize porogaramu ya AI ni imashini yiga imashini ubwayo?
    • Imibare ya sisitemu ishushanya ibyinjira mubisubizo hamwe nuburyo bwize
    • Umukoresha Imigaragarire ikubiyemo ibicuruzwa byose biranga
    • Urubuga rwurubuga icyitegererezo cyemerewe gusurwa
    • Inyandiko ya politiki isobanura uburyo itsinda rikoresha AI
  2. Itsinda rifite imipaka ntarengwa ya ms 100. Mu kizamini cyerekana amashusho, ninde mukandida wujuje?
    • Model B at 94% accuracy and 400 ms
    • Model A at 92% accuracy and 30 ms
    • Neither, because accuracy must be 100%
    • Both, because they score above 90%
  3. Niki kintu ni hyperparameter aho kuba ibipimo byize?
    • A weight value adjusted during training
    • A coefficient the fitted model uses for an input
    • A tree-depth limit selected through validation
    • A prediction returned for one example
  4. Sisitemu yo gushakisha itanga inyandiko yagaruwe kuri moderi mugihe cyibibazo. Ni izihe mpinduka zidafite imyitozo?
    • It necessarily retrains model weights
    • It fine-tunes the model on every query
    • It permanently changes the model version
    • It adds available evidence without changing model weights
  5. Iterambere rihuza neza icyitegererezo kurugero rwinyongera. Ni irihe hinduka?
    • Model weights, without guaranteeing the information is current
    • Only the text retrieved for one query
    • The application’s user interface but never the model
    • The validation set but not model behavior
  6. A team adapts a foundation model to a new document task. Which statement about this reuse is accurate?
    • It is necessarily the first AI model ever built
    • It can be adapted to multiple tasks, but still needs evaluation
    • It is only a model for building construction
    • It must be fine-tuned before it can answer any prompt
  7. Why should a team re-evaluate after changing a model version?
    • Interfaces always change whenever versions change
    • A new version makes latency measurements unnecessary
    • Behavior can change even while interfaces stay stable
    • A model name proves it is more accurate
  8. How should a team choose among candidate models for a defined application?
    • Select the largest parameter count by default
    • Use a leaderboard score without checking its errors
    • Choose the newest version without testing
    • Compare representative inputs, errors and operating constraints, then prefer the simplest adequate option