AIML Rounds

QUIZ

Unsupervised learning

8 questions on Unsupervised learning, from 7 lessons. Pick an answer in your head, then open it.

On the roadmap for: ML Engineering, Data Science.

  1. Question 1 of 8

    What does k-means minimise?

    1. A. The squared distance from points to their centres
    2. B. The distance between the cluster centres
    3. C. The classification error against true labels
    4. D. The number of clusters that it ends up using
    View answer

    ✓ A. The squared distance from points to their centres

    It alternates assigning points to the nearest centre and moving centres to the mean, which suits round, similar-sized clusters.

    Lesson: k-Means Clustering

  2. Question 2 of 8

    How can you choose k for k-means?

    1. A. Use the number of features in the data as the number of clusters
    2. B. Elbow, silhouette, and whether clusters make sense
    3. C. Always use 3 clusters, the usual default
    4. D. It doesn't matter: k-means picks k by itself
    View answer

    ✓ B. Elbow, silhouette, and whether clusters make sense

    No single rule is perfect; combine a metric with domain judgement.

    Lesson: k-Means Clustering

  3. Question 3 of 8

    What does hierarchical clustering give you that k-means doesn't?

    1. A. Probabilities of each point belonging to each of the clusters
    2. B. A tree of nested groups you can cut at any level
    3. C. Much faster training on large data
    4. D. Labels for each cluster automatically
    View answer

    ✓ B. A tree of nested groups you can cut at any level

    The linkage method (single, complete, average, Ward) shapes the tree.

    Lesson: Hierarchical Clustering

  4. Question 4 of 8

    Which clustering method finds curved clusters and labels points that belong to no cluster as noise?

    1. A. Linear regression
    2. B. PCA
    3. C. DBSCAN
    4. D. k-means
    View answer

    ✓ C. DBSCAN

    DBSCAN grows clusters through dense regions, so shape is flexible and isolated points become noise.

    Lesson: DBSCAN

  5. Question 5 of 8

    What does a Gaussian mixture model give that k-means doesn't?

    1. A. Fewer clusters than k-means for the same data
    2. B. Labels for brand-new classes
    3. C. Much faster results on large datasets with millions of rows
    4. D. Soft memberships and clusters with their own shapes
    View answer

    ✓ D. Soft memberships and clusters with their own shapes

    It's fitted with EM and suits overlapping, tilted clusters.

    Lesson: Gaussian Mixture Models

  6. Question 6 of 8

    Why should you scale features before PCA?

    1. A. Otherwise large-unit features dominate variance
    2. B. PCA only works on integer-valued features
    3. C. It isn't needed: PCA handles any feature scale
    4. D. Scaling removes all the outliers in the data
    View answer

    ✓ A. Otherwise large-unit features dominate variance

    PCA follows variance, and raw variance depends on units.

    Lesson: Principal Component Analysis

  7. Question 7 of 8

    In a t-SNE or UMAP plot, what should you NOT read into?

    1. A. The colours you used for each label
    2. B. That there are some groups in the data
    3. C. Which points are close neighbours in the original space
    4. D. The sizes of clusters and the gaps between them
    View answer

    ✓ D. The sizes of clusters and the gaps between them

    These methods keep local neighbourhoods but distort global distances and densities.

    Lesson: t-SNE & UMAP

  8. Question 8 of 8

    You have no fraud labels. How can an isolation forest flag unusual transactions?

    1. A. Odd points are isolated in fewer random splits
    2. B. It clusters transactions by colour
    3. C. It borrows fraud labels from similar companies instead
    4. D. It can't: anomaly detection needs labels
    View answer

    ✓ A. Odd points are isolated in fewer random splits

    Normal points need many splits to separate; rare, odd ones fall out quickly.

    Lesson: Anomaly Detection