순환 신경망 퀴즈

퀴즈를 풀면 정답과 설명이 나타납니다.

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. LSTM과 GRU는 일반 RNN에서 어떻게 개선됩니까?
   • 네트워크에서 모든 메모리를 제거합니다.
   • 텍스트가 아닌 숫자에만 작동합니다.
   • 데이터 없이 훈련합니다.
   • 그들은 게이트를 사용하여 어떤 정보를 유지, 업데이트 또는 폐기할지 제어합니다.
5. RNN은 어떤 유형의 데이터를 위해 특별히 설계되었나요?
   • 텍스트, 음성, 시계열 등의 순차적 데이터
   • 순서가 없는 단일 스틸 사진
   • 순서가 지정되지 않은 임의의 숫자
   • 3차원 건물 청사진만 해당
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?
   • 다섯
   • 하나
   • 세븐
   • 4개
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