Fundamentals of Machine Learning - PCA

The video tutorial introduces Principal Component Analysis (PCA), an unsupervised learning method. It covers the setup of the environment using libraries like Numpy and scikit-learn, and demonstrates the implementation of PCA on a dataset. The tutorial explains how to visualize PCA components and applies PCA to a human face dataset, highlighting how PCA can simplify data by focusing on key features.

What is the primary difference between supervised and unsupervised learning as discussed in the context of PCA?

• Both require labeled data.

• Supervised learning requires labeled data, while unsupervised learning does not.

• Neither requires labeled data.

• Unsupervised learning requires labeled data, while supervised learning does not.

Which library is NOT mentioned as part of the PCA implementation process?

• TensorFlow

• Seaborn

• Maplight

• Numpy

Which of the following is a key feature of PCA?

• It requires labeled data.

• It increases the number of features.

• It reduces the dimensionality of data.

• It is a supervised learning method.

What is the role of eigenvectors in PCA?

• They are used to scale the data.

• They serve as the principal components that explain the variance.

• They are used to normalize the data.

• They are used to label the data.

How are the principal components visualized in the context of PCA?

• As circles on a scatter plot.

• As lines on a line graph.

• As arrows or vectors on a scatter plot.

• As bars on a bar chart.

What is the purpose of using PCA on the human face dataset?

• To change the color of the images.

• To increase the resolution of the images.

• To extract the most significant facial features.

• To blur the images.

What is the main advantage of using PCA in data analysis?

• It requires more computational resources.

• It simplifies the data by reducing its dimensions.

• It adds noise to the data.

• It increases the complexity of the data.