Викторина, связанная с руководством · Средний Уровень
Викторина по закрытым повторяющимся единицам
Тестирует шлюзы GRU, обновления скрытых состояний, поведение при сбросе, различия LSTM, состояния-кандидаты и пределы архитектурных сравнений.
Вопрос 1 из 8
How many gates does the GRU cell in the guide use?
Предварительный просмотр каждого вопроса8 вопросы
Ответы и пояснения появляются по мере прохождения теста.
- How many gates does the GRU cell in the guide use?
- Two: an update gate and a reset gate
- Three plus a separate cell state
- One gate per sequence position
- No gates
- Что контролирует шлюз обновлений?
- Which input token is removed permanently
- The number of sequence layers
- Whether to compute a separate cell state
- How much of the previous hidden state to carry versus new candidate information
- Что контролирует ворота сброса?
- The final sequence length
- Скорость обучения оптимизатора
- How much past information is used when forming a candidate state
- Whether the update gate exists
- Как GRU представляет память по сравнению с LSTM?
- It uses a separate cell state and three gates
- It uses one hidden state rather than a separate cell state
- It has no recurrent state
- It stores the entire training sequence in the gates
- Что делает значение рядом с единицей для шлюза обновления GRU z?
- Favor the new candidate state over the previous hidden state
- Control how much past information is used in the reset-gated candidate
- Decide when the sequence should stop processing
- Carry most of the previous hidden state into the next state
- Почему шлюзование может помочь с долгосрочными зависимостями?
- It gives the model a learned route to preserve or update hidden information across steps
- It eliminates all recurrent computation
- It guarantees perfect memory at any length
- It turns a sequence into an unordered set
- What distinguishes a GRU candidate state from the prior hidden state?
- It is always the ground-truth next token
- It is computed from the current input and reset-gated past information
- It is copied unchanged from the input
- It stores a second LSTM cell
- What should be concluded from fewer GRU gates than LSTM gates?
- GRUs always outperform LSTMs
- GRUs cannot model sequences
- The architecture is simpler in this respect, but task performance still needs evaluation
- Fewer gates guarantee better accuracy