Quiz collegato alla guida · Medio Livello

Quiz sulle reti neurali ricorrenti

Esamina gli stati ricorrenti, gli input ordinati, le sfide del gradiente, i cancelli, il parallelismo di training, gli aggiornamenti numerici e i limiti della memoria di training.

Percorsi guida correlatiReti neurali ricorrenti
Domanda 1 di 8

What recurrent information does a conventional unidirectional RNN combine with each new input?

Anteprima di ogni domanda8 domande

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

  1. What recurrent information does a conventional unidirectional RNN combine with each new input?
    • Only the previous printed prediction with no internal state
    • A fresh unrelated dataset at every step
    • The previous hidden state
    • No parameters or intermediate information
  2. How should an RNN hidden state be understood?
    • An evolving internal representation that may summarize earlier inputs
    • A guaranteed lossless archive of every earlier input
    • The network's entire training dataset on disk
    • Only a final class label with no intermediate role
  3. Which training difficulty can arise from propagating RNN gradients through many time steps?
    • A guarantee that every hidden state grows without bound
    • Vanishing or exploding gradient magnitudes
    • An automatic change from speech to image inputs
    • Permanent deletion of the training objective
  4. In che modo LSTM e GRU migliorano rispetto ai semplici RNN?
    • Rimuovono tutta la memoria dalla rete
    • Funzionano solo sui numeri, non sul testo
    • Si allenano senza dati
    • Usano i controlli per controllare quali informazioni conservare, aggiornare o eliminare
  5. Per quale tipo di dati sono appositamente progettati gli RNN?
    • Dati sequenziali come testo, parlato e serie temporali
    • Fotografie singole senza ordine
    • Numeri casuali non ordinati
    • Solo progetti di edifici tridimensionali
  6. What training-computation difference does the original transformer architecture offer compared with a conventional sequential RNN?
    • Guaranteed fully parallel autoregressive generation
    • A guarantee that no training examples are needed
    • More parallel computation across training positions and direct attention interactions
    • A model with no learned parameters
  7. In the stated linear recurrent illustration h-new equals one-half h-previous plus x, what is h-new for h-previous two and x three?
    • Cinque
    • Uno
    • Sette
    • Quattro
  8. Why does a fixed-size RNN inference state not establish constant memory for full-sequence training?
    • Training never uses intermediate values
    • Backpropagation through time may store or recompute information across many steps
    • Every model deletes its parameters before learning
    • A fixed state guarantees every historical input is retained exactly