Quiz collegato alla guida · Medio Livello

Regressione Softmax per quiz di classificazione multiclasse

Esplora la normalizzazione softmax, l'interpretazione della probabilità multiclasse, il comportamento logit e le scelte di valutazione per prestazioni specifiche della classe.

Percorsi guida correlatiRegressione Softmax per multiclasse
Domanda 1 di 8

Quale vincolo soddisfano le probabilità softmax per un caso in tutte le classi modellate?

Anteprima di ogni domanda8 domande

Le risposte e le spiegazioni vengono visualizzate mentre rispondi al quiz.

  1. Quale vincolo soddisfano le probabilità softmax per un caso in tutte le classi modellate?
    • They sum to one for each case across modeled classes
    • They sum to one only when the highest-scoring class is correct
    • Their sum equals the number of classes
    • Each class score is converted independently without a shared denominator
  2. Un modello a tre classi restituisce probabilità 0,6, 0,3 e 0,1. Quale classe è la consueta previsione ad alta probabilità?
    • The first class, because it has the largest probability
    • The second class, because it has the largest probability
    • The third class, because it appears last
    • No class can be chosen until probabilities are converted to integer scores
  3. Perché l'aggiunta della stessa costante a ogni logit di classe lascia invariate le probabilità softmax?
    • Adding a constant changes only the denominator
    • Adding a constant changes only the numerator
    • The common exponential factor cancels between numerator and denominator
    • Softmax is invariant only when every logit is multiplied by the same constant
  4. Cosa implica l’ipotesi di output somma a uno riguardo alla configurazione target?
    • Several labels may be true together and are modeled independently
    • The classes are ordered and their numeric gaps are meaningful
    • The output may omit probability normalization across classes
    • Each case belongs to one of the modeled mutually exclusive alternatives
  5. Un classificatore ha un'elevata precisione complessiva ma un richiamo debole per una categoria rara. Quale rapporto aiuta a denunciarlo?
    • Overall accuracy and the number of examples in each class
    • Per-class recall or precision alongside a confusion matrix
    • Only aggregate training loss across all examples
    • The total number of model coefficients
  6. Why check the class-label ordering associated with probability columns?
    • Probability columns are always sorted from largest to smallest
    • Each column follows the raw input-file row order
    • Each probability column must be matched to its documented class label
    • The first column always represents the positive class
  7. Which training objective is commonly used for multinomial logistic regression?
    • Squared error between arbitrary integer class IDs
    • A hinge objective on the top two scores
    • Zero-one error as a smooth differentiable training loss
    • Multinomial cross-entropy or log loss
  8. A model ranks the correct class first but often assigns it 0.99 when it is right only about 0.7 of the time. What issue is present?
    • Poor calibration: confidence exceeds the observed success frequency
    • Poor recall: the predicted class is not the most frequent class
    • A violation of mutual exclusivity because confidence is high
    • A probability-sum error, even if all class probabilities sum to one