Clustering Algorithms Quiz

Hyperparameters in Algorithms

• The number of nearest neighbors to consider, learning rate, and number of iterations are hyperparameters in algorithms.

Decision Trees in Ensemble Methods

• Decision Trees are used in ensemble methods like Random Forest to reduce variance.

Sensitivity to Input Data Points

• DBSCAN is not sensitive to the order of input data points.

Handling Non-Linear Data

• Decision Trees can handle non-linear data.

K-Means

• The 'k' in K-means represents the number of clusters.
• K-means is primarily used for clustering.
• The number of clusters in K-means is determined by user input.
• K-means is sensitive to outliers.

Visualizing High-Dimensional Data

• t-SNE is suitable for visualizing high-dimensional data in lower dimensions.
• t-SNE can produce a visual representation of the data in 2D or 3D.

Distance Metric

• DBSCAN is sensitive to the choice of distance metric.

Handling Missing Values

• Decision Trees handle missing values by skipping the missing value during split evaluation.

Interpretability

• Decision Trees are known for their interpretability.

Clustering Algorithms

• DBSCAN is a density-based clustering algorithm that can detect arbitrarily shaped clusters.
• DBSCAN does not require the user to specify the number of clusters.

Dimensionality Reduction

• t-SNE is used for reducing the dimensionality of data while preserving the local structure.

Decision Trees

• Entropy is used in Decision Trees to measure impurity.
• Decision Trees can be used for both regression and classification.
• The main disadvantage of Decision Trees is that they are prone to overfitting.

Unsupervised Learning Algorithms

• DBSCAN and t-SNE are unsupervised learning algorithms.

t-SNE

• t-SNE stands for T-distributed Stochastic Neighbor Embedding.
• t-SNE is a type of unsupervised machine learning algorithm.
• The perplexity parameter in t-SNE controls the balance between the attention to local and global aspects of the data.