Ikibazo gihuza ibibazo · Hagati Urwego

Kwigenzura wenyine

Ongera usuzume intego zikomoka ku makuru, masike ya BERT, SimCLR ebyiri, ibikenewe byo gutangaza, guhuza n'imihindagurikire y'ikirere, imirimo ikurikira, imitwe ya projection, hamwe n'intego zangiritse.

Inzira zijyanye no kuyoboraKwigenzura wenyine
Ikibazo 1 Bya 8

Where does the supervision signal in the described self-supervised examples come from?

Reba buri kibazo8 ibibazo

Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.

  1. Where does the supervision signal in the described self-supervised examples come from?
    • A requirement for no training objective
    • Only new human semantic labels for every pretraining example
    • A rule that examples contain no useful information
    • The data and defined transformations of it
  2. Which input positions contribute prediction targets to the original BERT masked-language-model loss?
    • The positions selected for the MLM prediction task
    • Every position in the entire input regardless of selection
    • Only the first position of each new sentence
    • Only positions that appear after the final sentence boundary
  3. Mu myigire itandukanye nka SimCLR, 'couple nziza' ni:
    • Amashusho abiri adafitanye isano rwose
    • Ikirangantego cyanditswe n'abantu
    • Ibintu bibiri byongewe kumashusho amwe agomba kuba yegeranye mugushiramo umwanya
    • Amakopi abiri yamakuru
  4. What annotation requirement can self-supervised pretraining reduce in the described examples?
    • The need for any usable input data
    • Separate task-specific semantic labels for every pretraining example
    • All computational cost by definition
    • The need to assess downstream performance
  5. How can a representation learned through self-supervision be used for a later task?
    • By evaluating a task head or adapting the representation through fine-tuning
    • By assuming every target task requires no labels or validation
    • By discarding all representations before making predictions
    • By treating the pretraining loss as proof of every application's accuracy
  6. Nigute uburyo bwa GPT-moderi yimikorere yiyobora itandukanye na BERT?
    • Ntabwo ikoresha inyandiko na gato
    • Irasaba ibirango byintoki kuri buri jambo
    • Ihanura gusa ijambo ryambere ryinyandiko
    • Ihanura ikimenyetso gikurikira aho kuzuza ibimenyetso byapfunditswe
  7. In the original SimCLR framework, which component is discarded for the reported downstream representation use?
    • The encoder representation itself
    • The contrastive projection head
    • All training inputs before pretraining begins
    • The positive-pair source-image relationship
  8. When original BERT pretraining replaces a selected input position with a random token, what remains its loss target?
    • The newly inserted random token
    • The next sentence's first token in every case
    • The original token before replacement
    • No target, because every random replacement is omitted from training