Guide-yakabatana mibvunzo · Zvakaoma Nhanho

Batch Normalization Quiz

Inotarisa nhamba dzebatch, affine chiyero uye shanduko, inomhanya mavhareji, diki-batch kusagadzikana uye kuti BatchNorm inosiyana sei neLayerNorm.

Nzira dzekutungamira dzinoenderanaBatch Normalization
Mubvunzo 1 ye 8

Chii chinoita batch normalization normalize?

Tarisa mubvunzo wese8 mibvunzo

Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.

  1. Chii chinoita batch normalization normalize?
    • Izvo zvinopinza kune layer, pamienzaniso mune yazvino mini-batch
    • Iwo ekupedzisira ekubuda mavara etiweki
    • The kudzidza mwero purogiramu nekufamba kwenguva
    • Saizi yedataset yekudzidziswa
  2. Nei batch normalization ichisanganisira inodzidziswa paramita gamma uye beta?
    • Kuwedzera saizi yedataset
    • Kurega chiyero chetiweki uye kuchinjisa maitiro akajairwa, kuchengetedza simba rekumiririra
    • Kudonhedza zvisina tsarukano neurons panguva yekudzidziswa
    • Kuverenga basa rekurasikirwa
  3. Chii chinowanzo taurwa chinobatsira chebatch normalization?
    • Inobvisa kudiwa kwechero data yekudzidziswa
    • Inovimbisa iyo modhi haigone kudarika
    • Inobvumira mwero wekufunda wepamusoro uye nekukurumidza, kugadzikana kwakagadzikana
    • Inobvisa kudiwa kwekuita basa rekuita
  4. Panguva yekufungidzira (kufanotaura nezve data nyowani), ndedzipi nhamba dzinoshandiswa nebatch normalization?
    • Kurevesa uye musiyano weiyo yazvino inopinza chete
    • Zviverengero zvakangogadzirwa nguva imwe neimwe
    • Huwandu hwebvunzo seti hwakaverengerwa pachine nguva
    • Kumhanya maavhareji ezvinoreva uye musiyano wakaunganidzwa panguva yekudzidziswa
  5. Sei batch normalization ichigona kuita zvisina kunaka nemadiki madiki saizi?
    • Batch statistics inova ine ruzha uye isingavimbike fungidziro yekugovera kwechokwadi
    • Mabhechi madiki anoita kuti modhi iwedzere kuwanda kuti ikwane mundangariro
    • Iyo inodzima iyo activation mabasa
    • Mabheti madiki anomanikidza kushandiswa kweL1 kurongeka
  6. Ndeipi nzira yekujairisa inonyanya kushandiswa mushanduko yezvivakwa seimwe nzira ye batch normalization?
    • Dropout normalization
    • Layer normalization
    • L2 normalization yekurasikirwa
    • Gradient clipping
  7. Why does BatchNorm use running averages during inference instead of the current test batch’s statistics?
    • To retrain the model on test data
    • To make all activations exactly zero
    • So a prediction does not depend on which other examples happen to share the batch
    • To eliminate learned gamma and beta
  8. Where is BatchNorm commonly placed within a layer block according to the guide?
    • Only after the final prediction
    • Before the input data are loaded
    • Inside the optimizer update
    • Between the linear transformation and its activation function