Ikibazo gihuza ibibazo · Hagati Urwego

Isubiramo rya Neural Networks Ikibazo

Ongera usubiremo ibisubirwamo, byateganijwe byongeweho, imbogamizi zingirakamaro, amarembo, imyitozo ibangikanye, ivugurura ryumubare, hamwe namahugurwa-yibuka.

Inzira zijyanye no kuyoboraImiyoboro ya Neural Isubiramo
Ikibazo 1 Bya 8

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

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  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. Nigute LSTMs na GRUs bitezimbere kuri RNN isanzwe?
    • Bakuraho ububiko bwose kuri neti
    • Bakora gusa kumibare, ntabwo ari inyandiko
    • Bahugura nta makuru
    • Bakoresha amarembo kugirango bagenzure amakuru yo kubika, kuvugurura, cyangwa guta
  5. Ni ubuhe bwoko bw'amakuru RNNs yagenewe cyane cyane?
    • Amakuru akurikiranye nk'inyandiko, imvugo, hamwe n'ibihe bikurikirana
    • Ifoto imwe iracyari ifoto idafite gahunda
    • Imibare idasanzwe
    • Igishushanyo mbonera cyinyubako eshatu gusa
  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?
    • Bitanu
    • Imwe
    • Birindwi
    • Bane
  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