Ikibazo gihuza ibibazo · Hagati Urwego
Isesengura ry'ivangura rishingiye ku murongo
Ongera usuzume ibyiciro bya LDA na projection, gusangira-covariance ibitekerezo, ibipimo bivangura, no gutandukanya PCA.
Ikibazo 1 Bya 8
Kuki ibyiciro rusange bya LDA bitanga imipaka ifata imipaka?
Reba buri kibazo8 ibibazo
Ibisubizo nibisobanuro bigaragara mugihe ufata ikibazo.
- Kuki ibyiciro rusange bya LDA bitanga imipaka ifata imipaka?
- It uses class-specific covariance matrices in every case
- It maximizes total feature variance without labels
- Classes share a covariance matrix in its usual Gaussian model
- It ignores class priors whenever class sizes differ
- Nigute LDA ihitamo icyerekezo cyerekana uruhare rwayo rwo kugabanya?
- Maximize total variance without labels
- Favor class separation relative to within-class variation
- Choose features only by their marginal variance
- Keep only the original columns with largest means
- Hamwe na K ibyiciro byibuze K ukuyemo kimwe cyo kwinjiza ibintu, ni ubuhe buryo bwo hejuru bukoreshwa ku mubare w'ingirakamaro za LDA zivangura?
- K squared
- K
- The number of observations
- K minus one
- Which objective does PCA optimize in contrast to LDA?
- High overall variance without using class labels
- Class posterior probability
- Maximum class separation using labels
- Minimum classification error at every threshold
- Ni ryari icyerekezo gito-cyerekezo gifite akamaro kuri LDA?
- When it has the smallest variance regardless of labels
- Only when PCA has already chosen it
- When it separates labeled classes
- Only when every class has the same mean on it
- Ni izihe mpinduka mu isesengura rishingiye ku ivangura ugereranije na LDA isanzwe?
- Each class must have the same prior probability
- Each class may have its own covariance matrix
- Every class mean is constrained to be equal
- All quadratic terms are removed from the class comparison
- Why can LDA be numerically difficult when features greatly outnumber examples?
- The number of classes must automatically become larger
- Class priors cannot be estimated from any labeled sample
- The shared-covariance assumption removes every conditioning problem
- Covariance estimates may be singular or unstable
- A plot shows separated training groups after LDA projection. What has not yet been established?
- Reliable generalization on held-out data
- That labels influenced the projection
- That a projection was computed
- That classes were present in training