Idanwo ti o sopọ mọ itọsọna · Alabọde Ipele

Idanwo Ẹkọ Abojuto Ara-ẹni

Review data-derived targets, BERT masking, SimCLR pairs, annotation needs, adaptation, next-token tasks, projection heads, and corrupted-token targets.

Jẹmọ itọsọna awọn ọnaẸkọ Abojuto ti ara ẹni
Ibeere 1 ti 8

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

Awotẹlẹ gbogbo ibeere8 ibeere

Awọn idahun ati awọn alaye han bi o ṣe n mu ibeere naa.

  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. Ni ẹkọ iyatọ bi SimCLR, 'meji rere' jẹ:
    • Meji patapata jọmọ images
    • Awọn aami meji ti eniyan kọ
    • Awọn iwo afikun meji ti aworan kanna ti o yẹ ki o sunmọ ni aaye ifibọ
    • Meji idaako ti awọn dataset
  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. Bawo ni iṣẹ-ṣiṣe abojuto ara ẹni ti awoṣe GPT ṣe yatọ si ti BERT?
    • Ko lo ọrọ rara
    • O nilo awọn aami afọwọṣe fun gbogbo ọrọ
    • O sọ asọtẹlẹ ọrọ akọkọ ti iwe-ipamọ nikan
    • O ṣe asọtẹlẹ ami atẹle dipo ki o kun awọn ami ti o boju-boju
  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