MLA_Lec3

What is the main objective of the Bagging (Bootstrap Aggregating) technique in machine learning?

• To reduce the variance of the model

• • To increase the variance of the model

• • To reduce the data size

• • To reduce the bias of the model

In Bagging, how are the individual models trained?

• On different subsets of the original dataset, created by sampling with replacement

• On different random subsets without replacement

• On the entire dataset

• On a single sample of data

 Feature mappings in linear regression are used to

• Increase the dimensionality of the input data to capture non-linear relationships.

•  Randomly shuffle the data to avoid bias.

• Reduce the number of features to prevent overfitting.

• Convert categorical data into numerical data.

Which of the following is true about overfitting in a linear regression model?

• It occurs when the model has too few parameters and underfits the data

• It occurs when the model fits the training data too well but performs poorly on new data.

• It is always desirable as it minimizes the training error

• It can be avoided by increasing the complexity of the model.

Which of the following best describes vectorization in the context of linear regression?

• • Adding more features to the model to increase its complexity.

• • Using for-loops to iterate through each data point individually.

• • Reducing the number of features to prevent overfitting.

• Representing computations in terms of matrices and vectors to improve computational efficiency.

In linear regression, the goal is to find the weight vector that minimizes the .................between the predicted and actual outputs.

In gradient descent, the............... controls the size of the steps taken towards the minimum of the loss function.

The ............is a function that quantifies the error between the predicted output and the actual output, guiding the optimization process.

In the context of linear regression, adding................  to the model helps prevent overfitting by constraining the size of the model parameters

A................. is a technique used to transform the original input features into a new space where a linear model might perform better.