Guide-yakabatana mibvunzo · Pakati Nhanho
Regularization Quiz
Tarisa zvibodzwa zvenguva dzose, zvirango zveL1 neL2, kusiya chikoro, kukurumidza kumira, simba rechirango, uye mienzaniso yenhamba yechinangwa chakajairwa.
Mubvunzo 1 ye 8
Why would a practitioner add regularization when a model fits training-specific noise?
Tarisa mubvunzo wese8 mibvunzo
Mhinduro uye tsananguro zvinoonekwa paunenge uchitora bvunzo.
- Why would a practitioner add regularization when a model fits training-specific noise?
- To guarantee zero training error
- To remove the need for validation data
- To guarantee a faster GPU kernel
- To discourage overfitting and evaluate whether unseen-data performance improves
- Ndeipi nzira yenguva dzose ingangonyanya kutyaira mamwe masimbi kusvika zero, achinyatso kusarudza maficha?
- L2 kurongeka (kuora uremu)
- L1 kugadzirisa
- Batch normalization
- Kuwedzera mwero wekudzidza
- Kuregedza kunogadzirisa sei neural network panguva yekudzidziswa?
- Inobvisa zvidimbu zvachose kubva kunetiweki
- Iyo inowedzera zviyero zvine squared kune basa rekurasikirwa
- Inodzima neuron kamwe nekamwe nhanho kuti isakwanise kuenderana
- Inomira kudzidziswa kana kurasikirwa kwekusimbisa kuchikwira
- Mukurasikirwa kwakajairwa 'kukanganisa + lambda × chirango', kuwedzera lambda kunoitei?
- Inosimbisa chirango, ichisundira modhi kune mhinduro dzakareruka
- Inoderedza chirango uye inobvumira huremu hombe
- Inobvisa izwi rekukanganisa zvachose
- Haina simba pazviyereso
- Nei kukurumidza kumira kuchigona kurangarirwa sechimiro chenguva dzose?
- Nokuti inowedzera chirango chekurema pakurasikirwa
- Nekuti inomisa kudzidziswa modhi isati yatanga kuisa ruzha mu data
- Nekuti inowedzera modhi kugona nekufamba kwenguva
- Nekuti inongobvisa neurons
- What can happen when regularization is strengthened beyond what a task needs?
- Both training and test accuracy must improve
- The penalty becomes unrelated to the objective
- Validation becomes unnecessary
- The model can underfit useful structure even if variance decreases
- For a regularization example with weights minus two and one, what are the unscaled L1 and sum-of-squares L2 penalties?
- L1 is three and L2 is five
- L1 is minus one and L2 is three
- L1 is five and L2 is three
- Both penalties are minus two
- A regularized objective has prediction error two, lambda one-half, and penalty six. What is its total value?
- Zvisere
- Vatatu
- Vashanu
- Imwe