Guide-yakabatana mibvunzo · Pakati Nhanho

Zvishoma-kune-Zvakanyanya Kukurudzira Mibvunzo

Edza kuti Zvishoma-kusvika-Zvizhinji zvinoodza sei mibvunzo yakaoma uye inoshandisa mhinduro dzakatevedzana kuvandudza zviri nyore-kune-zvakaoma generalization.

Nzira dzekutungamira dzinoenderanaZvishoma Kunyanya Kukurudzira
Mubvunzo 1 ye 8

Ndeapi matanho makuru maviri eIno-ku-Kunyanya-kukurudzira?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Ndeapi matanho makuru maviri eIno-ku-Kunyanya-kukurudzira?
    • Gadzirisa dambudziko kuita subquestions, wozozvigadzirisa zvakarongeka
    • Chitima wobva wagadzirisa
    • Encode ipapo decode
    • Enzanisa mhinduro dzakawanda wozovhota
  2. Ko Zvishoma-ku-Zvizhinji zvinosiyana sei kubva kune yakajairwa ketani-ye-yekufunga kukurudzira?
    • Haishandisi mienzaniso zvachose
    • Inobvisa dambudziko pachena uye inopa mhinduro yega yega munhanho inotevera
    • Zvinoda kunyatsogadzirisa modhi
    • Inoshanda chete pamifananidzo
  3. What kind of task does the SCAN benchmark use to test compositional generalization?
    • Classifying satellite images of fishing vessels
    • Predicting fuel use from ship weather data
    • Interpreting natural-language commands that combine primitive actions
    • Aligning speech frames with handwritten characters
  4. Sei kurongeka kwemibvunzo kunokosha?
    • Hazvisizvo; kurongeka kunongoitika
    • Mibvunzo inotevera inofanira kuuya pekutanga
    • Kurongeka kunongokanganisa mafomati
    • Mubvunzo wega wega unofanirwa kungotsamira pane zvakatogadziriswa zvisati zvaitika
  5. Mhinduro dzepakati dzinoshandiswa sei panguva yekugadzirisa?
    • Iwo anowedzerwa kune akapoteredza kuitira kuti gare gare matanho anogona kuvaka paari
    • Dzinoraswa mushure menhanho imwe neimwe
    • Vanotumirwa kune imwe muenzaniso
    • Iwo akaenzana kuva nhamba imwe
  6. Ndeipi njodzi yakakosha muCheni-Kune-Yakawanda?
    • Haikwanisi kushandisa mienzaniso
    • Mhinduro yediki isiriyo inogona kukanganisa matanho ese ekudzika
    • Inongoshanda mumutauro mumwe chete
    • Iyo inogara ichida GPU cluster
  7. What accuracy did the paper report for code-davinci-002 on the SCAN length split using Least-to-Most with 14 exemplars?
    • About 16%
    • 50% chaiyo
    • At least 99% on the reported setup
    • Zero, because no demonstrations were used
  8. Besides SCAN, which task areas did the Least-to-Most paper also evaluate?
    • Wildlife re-identification and acoustic classification
    • Ship routing and port scheduling
    • Image outpainting and watermark detection
    • Symbolic manipulation and math reasoning