स्व-पर्यवेक्षित शिक्षण प्रश्नोत्तरी

जैसे ही आप प्रश्नोत्तरी लेते हैं उत्तर और स्पष्टीकरण दिखाई देते हैं।

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. SimCLR जैसी विरोधाभासी शिक्षा में, एक 'सकारात्मक जोड़ी' है:
   • दो पूरी तरह से असंबंधित छवियां
   • मानव-लिखित लेबलों की एक जोड़ी
   • एक ही छवि के दो संवर्धित दृश्य जो एम्बेडिंग स्थान में करीब होने चाहिए
   • डेटासेट की दो प्रतियां
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. GPT-शैली मॉडल का स्व-पर्यवेक्षित कार्य BERT से किस प्रकार भिन्न है?
   • यह बिल्कुल भी टेक्स्ट का उपयोग नहीं करता है
   • इसमें प्रत्येक शब्द के लिए मैन्युअल लेबल की आवश्यकता होती है
   • यह केवल दस्तावेज़ के पहले शब्द की भविष्यवाणी करता है
   • यह नकाबपोश टोकन भरने के बजाय अगले टोकन की भविष्यवाणी करता है
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