Gids-gekoppelde quiz · Middelmatig Niveau
Terugkerende neurale netwerkenquiz
Bekijk terugkerende statussen, geordende invoer, gradiëntuitdagingen, poorten, trainingparallellisme, numerieke updates en trainingsgeheugenlimieten.
Vraag 1 van 8
What recurrent information does a conventional unidirectional RNN combine with each new input?
Bekijk elke vraag8 vragen
Antwoorden en uitleg verschijnen terwijl je de quiz doet.
- 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
- 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
- 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
- Hoe verbeteren LSTM's en GRU's ten opzichte van gewone RNN's?
- Ze verwijderen al het geheugen van het netwerk
- Ze werken alleen met cijfers, niet met tekst
- Ze trainen zonder gegevens
- Ze gebruiken poorten om te bepalen welke informatie ze moeten bewaren, bijwerken of weggooien
- Voor welk type gegevens zijn RNN's speciaal ontworpen?
- Sequentiële gegevens zoals tekst, spraak en tijdreeksen
- Enkele foto's zonder bestelling
- Willekeurige ongeordende getallen
- Alleen driedimensionale blauwdrukken van gebouwen
- 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
- 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?
- Vijf
- Eén
- Zeven
- Vier
- 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