引導式測驗 · 中等 等級
自監督學習測驗
查看資料派生目標、BERT 遮罩、SimCLR 對、註釋需求、適應、下一個令牌任務、投影頭和損壞的令牌目標。
問題 1 的 8
Where does the supervision signal in the described self-supervised examples come from?
預覽每個問題8 問題
當您參加測驗時,就會出現答案和解釋。
- 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
- 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
- 在 SimCLR 等對比學習中,「正對」是:
- 兩張完全不相關的圖片
- 一對人工書寫的標籤
- 同一影像的兩個增強視圖在嵌入空間中應該接近
- 資料集的兩個副本
- 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
- 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
- GPT 式模型的自監督任務與 BERT 有何不同?
- 它根本不使用任何文字
- 每個單字都需要手動標籤
- 它僅預測文檔的第一個單字
- 它預測下一個標記,而不是填充屏蔽標記
- 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
- 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