Exploring Regression and Classification

What is the primary purpose of linear regression?

• To determine the correlation between two variables.

• To visualize data in a scatter plot.

• To predict the value of a dependent variable based on the values of independent variables.

• To calculate the mean of a dataset.

How does logistic regression differ from linear regression?

• Logistic regression requires normally distributed data; linear regression does not.

• Logistic regression predicts probabilities for categorical outcomes; linear regression predicts continuous values.

• Logistic regression is used for time series forecasting; linear regression is not.

• Linear regression can only handle binary outcomes; logistic regression can handle multiple outcomes.

What is the main idea behind support vector machines?

• The main idea behind support vector machines is to find the optimal hyperplane that maximizes the margin between different classes.

• Support vector machines primarily focus on regression analysis rather than classification.

• Support vector machines are used to reduce the dimensionality of data.

• The main idea is to cluster data points into groups without any boundaries.

How do support vector machines handle non-linear data?

• Support vector machines use the kernel trick to map non-linear data into a higher-dimensional space for linear separation.

• Support vector machines use decision trees for non-linear data.

• Support vector machines only work with linear data.

• Support vector machines ignore non-linear data completely.

In your own words, what does the term 'overfitting' mean in machine learning?

What is the assumption made by the Naive Bayes algorithm?

• Features are dependent on the class label.

• Features are independent of each other regardless of the class label.

• Features are conditionally independent given the class label.

• All features are equally important regardless of the class label.

In which scenarios is Naive Bayes particularly effective?

• Real-time data processing with dynamic features

• Small datasets with complex relationships

• Text classification, spam detection, large datasets, and independent features.

• Image recognition, where features are highly correlated

What type of problems is linear regression best suited for?

• Linear regression is used for predicting discrete values.

• Linear regression is best for classifying categorical outcomes.

• Linear regression is ideal for solving non-linear problems.

• Linear regression is best suited for predicting continuous outcomes based on linear relationships.

What is the output of a logistic regression model?

• Continuous values for regression analysis

• Binary outcomes of 0 or 1

• Probabilities between 0 and 1 for class membership

• Categorical labels for each class

What is the role of the kernel in support vector machines?

• The kernel transforms input data into a higher-dimensional space to enable better separation for classification.

• The kernel reduces the dimensionality of the data for faster processing.

• The kernel is responsible for selecting the training data points.

• The kernel acts as a regularization parameter in the model.