Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska Unugyada Xasuusta ee Muddada-Gaaban

Tijaabi doorarka iridda LSTM, haysashada gobolka-unugga, gelinta iyo xakamaynta wax soo saarka, cusboonaysiinta dheeriga ah, socodka qulqulka, iyo xaddidaadaha isku xigxiga.

Wadooyinka haga ee la xidhiidhaUnugyada xusuusta muddada gaaban
Su'aal 1 ee 8

In a common modern three-gate LSTM variant, which gates regulate cell information and exposed output?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. In a common modern three-gate LSTM variant, which gates regulate cell information and exposed output?
    • Akhri, qor, oo fur albaabbada
    • Bilow, jooji, oo jooji albaabbada
    • Illow, gelid, iyo albaabbada wax soo saarka
    • Cod, code, oo ka soo qayb gal albaabbada
  2. What training difficulty was LSTM designed to mitigate?
    • Meelo badan oo lagu kaydin karo
    • Vanishing gradients during learning over long sequences
    • Awood la'aanta isticmaalka GPU-ga
    • La'aanta shaqada firfircoonida
  3. Yaa soo bandhigay LSTM, iyo sanadkee?
    • Vaswani iyo asxaabtiisa 2017
    • Rumelhart iyo Hinton sanadkii 1986
    • LeCun iyo Bengio sanadkii 2012
    • Hochreiter iyo Schmidhuber ee 1997
  4. In a common LSTM cell update, why can the additive cell-state path help gradient flow?
    • It reduces reliance on repeated multiplicative transformations across time steps
    • Waxay ku dhufataa gobolka tiro badan tillaabo kasta
    • Waxay tirtirtaa gobolka tallaabo kasta
    • Waxay qaboojisaa dhammaan miisaanka inta lagu jiro tababarka
  5. Waa maxay shaqada firfircoonida ee irdaha LSTM sida caadiga ah u isticmaalaan inay u dhaqmaan sida daar/daminta jilicsan?
    • ReLU, soo saarista 0 ilaa xad la'aanta
    • Softmax oo ka sarreeya ereyada
    • Shaqo tillaabo ah oo si sax ah u soo saarta 0 ama 1
    • Sigmoid, oo soo saaray 0 ilaa 1
  6. Waa maxay sababta ay Transformers si weyn ugu beddeleen LSTM-yada qaabaynta luqadda ballaaran?
    • Transformers gabi ahaanba ma xamili karaan qoraalka
    • LSTMs uma baahna tababar
    • Transformers-ku waxay isbarbar-dhigaan si isku xigxig ah oo waxay qabtaan macnaha muddada-dheer iyadoo loo eegayo dareenka
    • Transformers waxay isticmaalaan tirooyin aad uga yar wadar ahaan
  7. If an LSTM forget gate is near one and its input gate near zero, what happens to the cell state?
    • It largely retains the previous state
    • It is forced to zero
    • It becomes the raw input token
    • It must reverse the sequence
  8. Which gate controls how much of an LSTM cell’s stored state is exposed as output?
    • The forget gate alone
    • The output gate
    • The optimizer momentum term
    • The positional encoding gate