Thanks to visit codestin.com
Credit goes to www.scribd.com

Scribd
Upload
17 views3 pages

ML 2 Marks Quick Revision

The document provides a quick revision guide for machine learning, covering key concepts, formulas, and definitions across various topics including regression, classification, neural networks, unsupervised learning, dimensionality reduction, and evaluation methods. It includes specific formulas for linear regression, logistic regression, K-means, and accuracy, among others. Additionally, it defines important terms such as bias, variance, and the perceptron algorithm.

Uploaded by

pranav1256kam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
17 views3 pages

ML 2 Marks Quick Revision

The document provides a quick revision guide for machine learning, covering key concepts, formulas, and definitions across various topics including regression, classification, neural networks, unsupervised learning, dimensionality reduction, and evaluation methods. It includes specific formulas for linear regression, logistic regression, K-means, and accuracy, among others. Additionally, it defines important terms such as bias, variance, and the perceptron algorithm.

Uploaded by

pranav1256kam
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 3

Machine Learning Quick Revision - 2 Marks Questions with Formulas

Introduction
1. Define machine learning.

2. List any four applications of machine learning.

3. Mention any two machine learning software tools.

Parametric Regression
4. Write the formula for simple linear regression.

y= +x+

5. Write the formula for multiple linear regression.

y = + x + x + ... + x +

6. What is the formula for polynomial regression (degree 2)?

y= +x+x+

7. Write the cost function for linear regression.

J() = (1/2m) (h_(x) - y)

8. Gradient descent update rule for linear regression.

:= - (1/m) (h_(x) - y)x

9. Formula for normal equation.

= (XX)Xy

Generative Learning
10. Define Gaussian parameter estimation.

11. Write formula for mean and variance.

= (1/m) x, = (1/m) (x - )

12. What is maximum likelihood estimation?

13. Define bias and variance.

Classification
14. Write the sigmoid function used in logistic regression.

h_(x) = 1 / (1 + e^(-x))

15. Write cost function for logistic regression.

J() = - (1/m) [ylog(h_(x)) + (1 - y)log(1 - h_(x))]

16. Gradient descent update for logistic regression.

:= - J()

17. How is overfitting avoided?

18. What is the regularized cost function?

J() = J + (/2m)

Neural Networks
19. What is the perceptron algorithm?

20. Write the output formula of a neuron.

y = f(wx + b)

21. What is backpropagation?

22. Define learning curve.

Unsupervised Learning
23. Write the objective function for K-means.

J = ||x - ||

24. What is dendrogram?

25. What is latent Dirichlet allocation used for?

Dimensionality Reduction
26. What is PCA and its main goal?

27. Formula for PCA covariance matrix.

= (1/m) (x - )(x - )

28. What is LDA?


Evaluation Methods
29. Write the formula for accuracy.

Accuracy = (TP + TN) / (TP + TN + FP + FN)

30. Define confusion matrix.

31. Write formula for precision and recall.

Precision = TP / (TP + FP), Recall = TP / (TP + FN)

32. What is F1 score?

F1 = 2 * (Precision * Recall) / (Precision + Recall)

33. Write the formula for log loss.

- (1/m) [ylog(p) + (1 - y)log(1 - p)]

34. What is the elbow method used for?

35. What is silhouette score?

s(i) = (b(i) - a(i)) / max(a(i), b(i))

You might also like