Kuis Jaringan Neural Berulang

Jawaban dan penjelasan muncul saat Anda mengikuti kuis.

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. Bagaimana peningkatan LSTM dan GRU pada RNN biasa?
   • Mereka menghapus semua memori dari jaringan
   • Mereka hanya bekerja pada angka, bukan teks
   • Mereka berlatih tanpa data apa pun
   • Mereka menggunakan gerbang untuk mengontrol informasi apa yang harus disimpan, diperbarui, atau dibuang
5. Jenis data apa yang dirancang khusus untuk RNN?
   • Data berurutan seperti teks, ucapan, dan deret waktu
   • Foto tunggal tanpa urutan
   • Nomor acak yang tidak berurutan
   • Cetak biru bangunan tiga dimensi saja
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?
   • Lima
   • Satu
   • Tujuh
   • Empat
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