Kedis ku xidhan hagaha · Dhexdhexaad Heerka

Kediska Models-ilaa-Isxigxiga

Baro sida moodooyinka cod-dejiyeyaashu u kharibaanayaan taxanaha gelinta ee soo saarista dhererka kala duwan iyadoo la adeegsanayo hababka feejignaanta iyo feejignaanta.

Wadooyinka haga ee la xidhiidhaTaxanaha Tusaha Qaababka
Su'aal 1 ee 8

Waa maxay labada qaybood ee ugu muhiimsan ee qaabka isku xigxiga?

Horudhac su'aal kasta8 su'aalo

Jawaabaha iyo sharraxaadaha waxay soo baxayaan markaad qaadanayso kediska.

  1. Waa maxay labada qaybood ee ugu muhiimsan ee qaabka isku xigxiga?
    • Cod-bixiye iyo cod-bixiye
    • Calaamade iyo kala-saar
    • Laba cod-bixiyeyaal isku mid ah
    • Filter iyo darajo
  2. Dhibaato noocee ah ayaa habka feejignaanta ku xaliyay moodooyinka seq2seq?
    • Calaamadaynta tartiib tartiib ah
    • Dhererka dhererka go'an ee lafdhabarta vector ee wax gelinta dheer
    • La'aanta eray bixin
    • Xogta tababarka ee xad dhaafka ah
  3. Nashqada noocee ah ayaa isticmaalay qaabka tarjumaadda seq2seq ee asalka ah ee 2014?
    • Shabakado kacaan ah
    • Go'aan geedaha
    • LSTM-yada is dulsaaran
    • Lakabyo quudin qaawan
  4. Sidee bay fiiro gaar ah u dhistaa macnaha guud ee tallaabo kasta oo wax lagu kala saarayo?
    • Marka la isku celceliyo dhammaan calaamadaha wax gelinta si isku mid ah
    • Adigoo iska indhatiraya cod-bixiyaha gabi ahaanba
    • Adigoo koobiyaynaya calaamada wax galinta ee ugu danbeysa
    • Marka la eego wadar miisaan leh oo ah gobolo cod-bixiye ah oo isticmaalaya buundooyinka isku toosinta
  5. Waa maxay sababta wax-soo-saarka seq2seq uga duwanaan karaa dhererka agabka?
    • Decoder-ku wuxuu abuuraa calaamado ilaa uu ka soo saaro calaamad joogsi
    • Wax-soo-gelinta iyo soo-saarku had iyo jeer waa siman yihiin dherer
    • Codeeyaha ayaa wax walba ku dhejinaya
    • Dhererka ayaa horay loo sii hagaajiyay
  6. Moodooyinka casriga ah waa kuwee kuwa caanka ah ee Transformer-ku-saleysan qaab-dhismeedka seq2seq?
    • ResNet iyo VGG
    • T5 iyo BART
    • K-macnaha iyo PCA
    • Word2Vec iyo GloVe
  7. In encoder-decoder attention, which representations are commonly used as keys and values?
    • Only the decoder’s future hidden states
    • The vocabulary file’s byte offsets
    • The encoder’s output representations
    • The optimizer’s learning-rate history
  8. What does a bidirectional encoder provide to an attention-based decoder?
    • A fixed one-token output regardless of the input
    • A guarantee that output length equals input length
    • A causal mask over future target tokens
    • Contextual representations of source tokens that can use information from both directions