7-Naive Bayes Flashcards

1
Q

What is the naive assumption in naive bayes?

A

All features (attributes) are conditionally independent on the class y

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
2
Q

What is the naive bayes algorithm?

A

y^ = argmax (y) P(y) * Product from i to n P(x_n | y)

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
3
Q

What are the naive bayes assumptions?

A

Features are conditionally independent
Instances are independent
Distribution of test data is the same as training data

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
4
Q

How do we manage unseen discrete features in naive bayes?

A

If any term hasn’t been seen before, we can:
- Epsilon smoothing: Set a small epsilon value
- Laplace smoothing: Add a pseudo count , (a + count())/ (Ma + count()), where Ma is the total count

How well did you know this?
1
Not at all
2
3
4
5
Perfectly
5
Q

How do we manage continuous features with zero variance in naive bayes?

A

Ignore feature

Add small smoothing value to standard deviation

How well did you know this?
1
Not at all
2
3
4
5
Perfectly