StudyFox
कीमतेंब्लॉगएक्सटेंशनमुफ़्त टूल
  • कीमतें
  • ब्लॉग
  • एक्सटेंशन
  • मुफ़्त टूल
  • शुरू करेंसाइन इन
StudyFox

अपने नोट्स, PDF और स्लाइड्स को फ़्लैशकार्ड, क्विज़, नोट्स और माइंड मैप में बदलें।

StudyFox खोलें

स्टडी टूल्स

  • होमवर्क हेल्पर
  • नोट मेकर
  • फ़्लैशकार्ड मेकर
  • क्विज़ मेकर
  • माइंड मैप मेकर

प्रोडक्ट

  • कीमतें
  • Chrome एक्सटेंशन
  • मुफ़्त एक्सटेंशन
  • स्टडी सेट देखें
  • ब्लॉग

सहायता

  • सहायता केंद्र
  • संपर्क करें
  • गोपनीयता नीति
  • सेवा की शर्तें

तुलना करें

  • Chegg का विकल्प
  • Course Hero का विकल्प
  • Coursology का विकल्प
  • Photomath का विकल्प
  • Gauthmath का विकल्प
  • PhotoSolve का विकल्प
  • CollegeTools का विकल्प
  • Transcript का विकल्प
  • SmartSolve का विकल्प
  • Homeworkify का विकल्प
  • AnswersAi का विकल्प
  • StudyX का विकल्प
  • Quizlet का विकल्प
  • Anki का विकल्प
  • Knowt का विकल्प
  • Brainscape का विकल्प
  • सभी तुलनाएँ

© 2026 StudyFox AI. सर्वाधिकार सुरक्षित।

  • X
  • Discord
  • Instagram
ExploreEngineering & TechData Science & AIMachine Learning Evaluation and Diagnosis: Hard Applied Quiz

Quiz · Hard

Machine Learning Evaluation and Diagnosis: Hard Applied Quiz

Multi-step problems on confusion-matrix metrics, base rates, gradient descent, cross-validation, leakage, ROC vs PR and diagnosing bias vs variance.

by Kill h.16 questionsCreated Nov 20, 2026, 08:27 PM
Data Science & AI· Machine LearningTags#machine-learning#metrics#exam-prep#evaluation

16 questions

  1. 1

    A classifier is evaluated on 1,000 examples: TP = 45, FP = 15, FN = 5, TN = 935. What are its precision and recall?

    • Precision 0.75, recall 0.90

    • B

      Precision 0.75, recall 0.75

    • C

      Precision 0.98, recall 0.90

    • D

      Precision 0.90, recall 0.75

    Precision = 45 / (45 + 15) = 0.75. Recall = 45 / (45 + 5) = 0.90. Swapping the two is the classic slip: precision uses FP in the denominator, recall uses FN.

  2. 2

    Using the same counts (TP = 45, FP = 15, FN = 5, TN = 935), what is the F1 score?

    • A

      0.75

    • B

      0.90

    • 0.83

    • D

      0.82

    F1 = 2TP / (2TP + FP + FN) = 90 / 110 = 0.818, which rounds to 0.82. If options differ only in the last digit, compute exactly: 2(0.75)(0.90)/1.65 = 0.818.

  3. 3

    A screening test: disease prevalence 2%, sensitivity 95%, specificity 90%. A random person tests positive. About what is the probability they have the disease?

    • A

      About 50%

    • B

      95%

    • C

      2%

    • About 16%

    Per 1000 people: 20 sick, of whom 19 test positive; 980 healthy, of whom 98 test positive. P = 19 / (19 + 98) = 0.162. The base rate dominates, which is why most positives are false alarms.

  4. 4

    Gradient descent on starts at with learning rate 1.1. What happens?

    • A

      It converges to 0 quickly

    • It oscillates with growing magnitude and diverges

    • C

      It converges to 0 slowly

    • D

      It stays at 4

    Each step gives . The sign flips and the magnitude grows by 20% per step: 4, -4.8, 5.76... Convergence needs , that is .

  5. 5

    In 5-fold cross-validation the fold accuracies are 0.82, 0.78, 0.85, 0.80 and 0.75. What is the mean estimate?

    • 0.80

    • B

      0.78

    • C

      0.82

    • D

      0.85

    (0.82 + 0.78 + 0.85 + 0.80 + 0.75) / 5 = 4.00 / 5 = 0.80. The median 0.80 happens to match here, but the reported cross-validation score is the mean.

  6. 6

    Training accuracy is 91% and validation accuracy is 90% on a task where human accuracy is 99%. What is the best next step?

    • A

      Add dropout or stronger regularization

    • Increase model capacity or train longer

    • C

      Collect more validation data

    • D

      Stop: the gap is small so the model is fine

    Both errors are high and close together, so the problem is bias (underfitting). A larger model, better features or longer training helps. Regularization would make underfitting worse.

  7. 7

    Which decision on a binary classifier moves a point along its ROC curve rather than changing the curve itself?

    • Changing the classification threshold

    • B

      Adding a new feature

    • C

      Switching from logistic regression to a random forest

    • D

      Training on more data

    Each threshold gives one (FPR, TPR) pair, tracing out the curve. Changing the model, features or data changes the scores and therefore the curve itself.

  8. 8

    Why can a random forest's out-of-bag score be used as a validation estimate?

    • A

      The forest is trained on a held-out set

    • Each tree is evaluated on rows it did not see in its bootstrap sample

    • C

      It uses the test set for pruning

    • D

      Out-of-bag rows are duplicated into the training data

    About 36.8% of rows are left out of each bootstrap sample, so each row can be scored by the trees that never trained on it. That gives an honest error estimate without a separate validation set.

  9. 9

    A feature has 200 distinct category values (e.g. zip code). Which encoding is most likely to blow up the dimensionality for a linear model?

    • One-hot encoding

    • B

      Target (mean) encoding with proper cross-fitting

    • C

      Hashing to 20 buckets

    • D

      Frequency encoding

    One-hot creates one column per category (200 here, thousands for real zip codes). The others give one or few columns. Target encoding needs care to avoid leaking the label.

  10. 10

    Which situation calls for precision-recall AUC rather than ROC AUC?

    • A

      Choosing k in k-means

    • B

      Regression on house prices

    • Detecting fraud where 0.1% of transactions are fraudulent

    • D

      A balanced data set of cats and dogs

    With extreme imbalance, ROC AUC can stay high while precision is poor, because FPR is computed over a huge negative class. PR curves expose that.

  11. 11

    You fit PCA on the full data, keep 10 components, then split into train and test and train a classifier. What is wrong?

    • A

      PCA should keep exactly 2 components

    • B

      Nothing, PCA is unsupervised so it cannot leak

    • C

      PCA cannot be used before a classifier

    • The test data influenced the components (leakage); PCA should be fit on training data only

    PCA is unsupervised but it still learns directions from the data it is shown. Fitting it on test rows lets test information shape the features and makes validation optimistic.

  12. 12

    A logistic regression model has intercept -3 and a single feature coefficient 1.5. What is the predicted probability when x = 2?

    • A

      0.27

    • B

      0.95

    • 0.5

    • D

      0.73

    z = -3 + 1.5(2) = 0, so p = σ(0) = 0.5. This x is exactly the decision boundary for a 0.5 threshold.

  13. 13

    Elastic net combines which two ideas?

    • A

      Bias and variance weighting

    • B

      Bagging and boosting

    • C

      k-means and PCA

    • L1 and L2 penalties

    Elastic net adds both lasso and ridge penalties, giving sparsity plus stable handling of correlated features, where lasso alone tends to pick one of a correlated group arbitrarily.

  14. 14

    A k-NN classifier with k = 1 is evaluated on its own training data. What is its training accuracy (assuming no duplicate points with different labels)?

    • A

      50%

    • 100%

    • C

      It depends on feature scaling only

    • D

      About the test accuracy

    Each training point is its own nearest neighbor, so it is always predicted correctly. That is why training accuracy is meaningless for k = 1, and why k must be chosen with validation data.

  15. 15

    A neural network's training loss keeps decreasing while validation loss starts to increase after epoch 12. What should you do?

    • Use early stopping near epoch 12 or add regularization

    • B

      Increase the learning rate

    • C

      Keep training: loss will recover

    • D

      Remove the validation set

    Rising validation loss with falling training loss is overfitting. Stop near the validation minimum, or add dropout, weight decay or more data.

  16. 16

    Which statement about k-means inertia is true?

    • A

      It is always minimized at k = 1

    • B

      It increases as k increases

    • It never increases as k increases (for the best clustering), so it cannot choose k alone

    • D

      It measures between-cluster separation

    Within-cluster sum of squares keeps shrinking as k grows, down to 0 at k = n. Hence the elbow method or the silhouette score is used to pick k. Inertia is largest at k = 1.