Lecture 7 – Fitted modelling

Question 1

What is regression?

Answer 1

looking for relationships amongst variables

Question 2

Purpose of using regression?

Answer 2

• to determine how multiple variables are related
• to predict a value

Question 3

What is polynomial regression?

Answer 3

fitting a curve defined by a polynomial function to data

Question 4

What is bias?

Answer 4

measures how much the prediction differs from the desired regression function

Question 5

What is variance?

Answer 5

measure how much the predictions for individual data sets vary around their average

Question 6

Describe the bias vs variance tradeoff
(With graph)

Answer 6

Underfitting happens when a model unable to capture the underlying pattern of the data. These models usually have high bias and low variance.

Overfitting happens when our model captures the noise along with the underlying pattern in data. It happens when we train our model a lot over noisy dataset. These models have low bias and high variance.

Question 7

What does the “no free lunch theorem” state?

Answer 7

If a learning algorithm performs well and a certain class of problem then it necessarily pays for that with lower performance on all other problems

Question 8

How can an ensemble be used in prediction?

Answer 8

ensemble = multiple models applied to the same problem
prediction result = average / majority vote of the ensemble