递归神经网络测验

当您参加测验时，就会出现答案和解释。

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. LSTM 和 GRU 如何改进普通 RNN？
   • 他们从网络中删除所有内存
   • 它们仅适用于数字，不适用于文本
   • 他们在没有任何数据的情况下进行训练
   • 他们使用门来控制保留、更新或丢弃哪些信息
5. RNN 专门针对哪种类型的数据而设计？
   • 序列数据，如文本、语音和时间序列
   • 无顺序的单张静态照片
   • 随机无序数
   • 仅三维建筑蓝图
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?
   • 五
   • 一
   • 七
   • 四
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