ML2 Yazeed Dimensionality Reduction

What is the purpose of Principal Component Analysis (PCA)?

• To increase the dimensionality of a dataset

• To remove outliers from the dataset

• To add noise to the dataset

• To reduce the dimensionality of a dataset

What is the nature of PCA?

• Supervised

• Reinforcement learning

• Semi-supervised

• Unsupervised

What is an advantage of PCA?

• Increases redundancy in the dataset

• Helps in visualizing high-dimensional data by increasing its dimensions

• Generates components that are uncorrelated

• Generates components that are highly correlated

What is a limitation of PCA?

• Insensitive to the scale and distribution of the data

• Does not overlook important relationships in the data

• Sensitive to the scale and distribution of the data

• Captures all relationships in the data

Which statistical measure is relevant to PCA for capturing variance?

• Median

• Interquartile Range

• Mean

• Mode

What do eigenvalues indicate in PCA?

• The amount of variance captured by each principal component

• The strength and direction of a linear relationship between two variables

• The direction of the axes of the new feature space

• The correlation between variables

What do eigenvectors provide in PCA?

• The direction of the axes of the new feature space

• The correlation between variables

• The amount of variance captured by each principal component

• The strength and direction of a linear relationship between two variables

What is the practical application of PCA?

• Speech recognition

• Text analysis

• Image processing

• Audio synthesis

What does PCA transform the original variables into?

• A new set of variables based on their eigenvalues and eigenvectors

• A new set of variables based on their covariance and correlation

• A new set of variables based on their mean and median

• A new set of variables based on their mode and interquartile range

What are the practical applications of PCA?

• Data visualization, data preprocessing, data cleaning, and data transformation

• Image processing, genome data analysis, market research, and financial data analysis

• Speech recognition, audio synthesis, text analysis, and video editing

• Face recognition, risk management, fraud detection, and consumer patterns