quiz bu lëkkale ak tegtal · Diggante Niveau
Lasso ak régression net elastik
Xoolaat ni L1 ak L2 daan yi di amee ci koeffisien yi, lu tax eskalaasioŋ ak cross-validation am solo, ak ni predictor yu korrele yi di amee ci tànneef bi.
Laaj 1 de 8
Ab lasso fit dafay jox ab coefficient bu nekk zero ci ab kàddu. Lan la loolu di tekki ci biir model bi ñu defar?
Xoolaatal laaj bu nekk8 laaj
Sooy def quiz bi, tontu yi ak leeral yi dañuy feeñ.
- Ab lasso fit dafay jox ab coefficient bu nekk zero ci ab kàddu. Lan la loolu di tekki ci biir model bi ñu defar?
- The feature is excluded from its linear prediction
- The feature has no association in every reasonable model
- The feature was removed during data preprocessing
- The feature has no variation in the source population
- Which penalty combination defines elastic net in the guide?
- L1 penalty with alpha denoting only the L1 share
- L1 plus L2
- L1 penalty only, with no L2 component
- L2 penalty with L1 used only during feature scaling
- Ñaari predictors yu am lu leen jëmé lool dañuy soppeeku ci biir lasso ci biir resamples. Lan la loolu di wone?
- Standardization guarantees stable selection whenever predictors are correlated
- Any change in selected features proves the test set leaked into cross-validation
- Their selection can be unstable despite similar predictions
- Lasso is guaranteed to assign identical coefficients across resamples
- Lu tax natt war nañu ko jàng ci biir cross-validation training fold bu nekk?
- Fit the scaler once on all rows, then split for cross-validation
- Fit scaling parameters on validation rows only
- Scale after selecting the final penalty using test data
- To keep validation-fold information out of preprocessing
- Ci mixing-ratio convention bi ñu gëna xam, fan la pure lasso di nekk?
- The endpoint with all L2 penalty
- The endpoint with all L1 penalty
- The endpoint with no penalty
- The setting that removes the intercept
- Ab dataset dafa am ay predictors yu ñu natt ci dollars ak ci ay fraction yu tuuti. Lu tax natt mën na am solo ci penalized regression?
- Feature scaling cannot affect penalty behavior when units change
- Rescaling the target is the only preprocessing relevant to coefficients
- The penalty acts on coefficient magnitudes, which depend on feature units
- Scaling after fitting leaves the selected coefficients unchanged
- When should a final test set be used if penalty settings are chosen by cross-validation?
- Only if training error is zero
- Repeatedly to choose each penalty value
- Before fitting the preprocessing pipeline
- After model selection, for a final evaluation
- Which statement about a zero lasso coefficient is appropriately cautious?
- It is a result of this penalized fit, not universal proof of no relationship
- It proves this predictor has no causal effect
- It will remain zero across populations and penalty settings
- It establishes that no nonlinear relationship exists