Machine Learning

Linear Methods For Classification

Interview questions on Linear Methods For Classification.

11 questions

All subtopics General Concepts Odds and Log-odds The Sigmoid Truly Understanding Logistic Regression The Logit Function and Entropy

The Logit Function and Entropy

Q1. The entropy of a single binary outcome with probability $p$ to receive 1 is defined as:$$

H(p) ≡ −p\log{p}−(1−p)\log(1−p) $$1. At what $p$ does $H(p)$ attain its maximum value? 2. What is the relationship between the entropy $H(p)$ and the logit function, given $p$ ?

The Logit Function and Entropy

Q2. What is the difference between linear regression and logistic regression?

The Logit Function and Entropy

Q3. What is the logistic function (sigmoid function), and how is it used in logistic regression?

The Logit Function and Entropy

Q4. What is the purpose of the odds ratio in logistic regression?

The Logit Function and Entropy

Q5. What is the cost function in logistic regression, and why is it used?

The Logit Function and Entropy

Q6. What are the assumptions of logistic regression?

The Logit Function and Entropy

Q7. How do you deal with multi-collinearity in logistic regression?

The Logit Function and Entropy

Q8. What is the purpose of regularization in logistic regression, and how does it work?

The Logit Function and Entropy

Q9. What is the ROC curve in the context of logistic regression?

The Logit Function and Entropy

Q10. How do you evaluate the performance of a logistic regression model?

The Logit Function and Entropy

Linear Methods For Classification

Q1. The entropy of a single binary outcome with probability $p$ to receive 1 is defined as:$$

Q2. What is the difference between linear regression and logistic regression?

Q3. What is the logistic function (sigmoid function), and how is it used in logistic regression?

Q4. What is the purpose of the odds ratio in logistic regression?

Q5. What is the cost function in logistic regression, and why is it used?

Q6. What are the assumptions of logistic regression?

Q7. How do you deal with multi-collinearity in logistic regression?

Q8. What is the purpose of regularization in logistic regression, and how does it work?

Q9. What is the ROC curve in the context of logistic regression?

Q10. How do you evaluate the performance of a logistic regression model?

Q11. For logistic regression, why is log loss recommended over MSE (mean squared error)?