Quiz collegato alla guida · Medio Livello

Quiz sulla condivisione difficile dei parametri nelle reti multi-tasking

Testa i tronchi condivisi, le teste delle attività, i contrasti di condivisione morbida, la ponderazione delle perdite, la competizione gradiente e la valutazione specifica dell'attività.

Domanda 1 di 8

Cosa significa condivisione rigida dei parametri?

Anteprima di ogni domanda8 domande

Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.

  1. Cosa significa condivisione rigida dei parametri?
    • Each task has a separate full network with a similarity penalty
    • Tasks share labels but no model parameters
    • One output head predicts every task without task identity
    • Tasks share a common hidden trunk and use task-specific output heads
  2. In cosa differisce la condivisione hard dalla condivisione soft dei parametri?
    • Soft sharing keeps separate task parameters and encourages them to remain similar
    • Soft sharing always uses one shared trunk
    • Hard sharing stores no parameters
    • The two terms mean the same architecture
  3. Perché la condivisione difficile può ridurre l’overfitting per attività correlate?
    • Each task receives more independent parameters
    • Shared layers learn features that must serve multiple tasks
    • The model avoids training data
    • All tasks are forced to use identical output labels
  4. Come vengono comunemente combinate le perdite di compiti per la formazione congiunta?
    • By choosing one task and ignoring the others
    • By averaging labels across tasks
    • As a weighted sum in a shared objective
    • By using only the smallest loss
  5. Cosa può accadere se prevalgono la perdita o i gradienti di un’attività?
    • All task heads disappear
    • The tasks become independent
    • The model automatically balances every gradient
    • The shared trunk may prioritize it while other tasks are under-served
  6. When is hard parameter sharing most suitable?
    • When tasks can benefit from useful shared representations
    • When every task is unrelated and incompatible
    • When a task must never influence another
    • When there is only one task
  7. What does a task-specific head usually do?
    • Stores all training examples
    • Maps shared features to that task’s output
    • Balances the gradients of every other task
    • Selects which hidden trunk to use per token
  8. What should be monitored when training a multi-task model?
    • Only the total parameter count
    • Only the largest task’s accuracy
    • Per-task performance and whether shared updates help or harm each task
    • The number of output heads alone