Supervised Learning - Prediction Week 3 Challenge

Question 1 explained in jupiter book below

question 2

Difference between MSE and MAE

The mean absolute error (MAE) measures how close the predictions are to the outcomes. It is considered as an average of the all absolute errors.

The mean squared error measures the average of the squares of the errors, which means the difference between the estimator and estimated. MSE is equivalent to the expected value of the squared error loss or quadratic loss. The difference occurs because of the randomness. The MSE is a measure of the quality of an estimator, it is always positive, and values which are closer to zero are better.

question 3

What are the different loss functions for regression

The different Loss Functions for Regression are :

Mean Squared Error

Mean Absolute Error

Mean Absolute Percentage Error

Root Mean Squared Error

Huber Loss

Log-Cosh Loss

question 4

What is the importance of learning rate

Learning rate determines the rate of speed at which the gradient moves during gradient descent.

Setting it too high would make the path instable and also having it too low would make convergence slow.

Further putting it to zero means the model isn't learning anything from the gradients

question 5

How to evaluate linear regression

To evaluate the linear regression we consider three metrices. The following are the three metrices considered:

1) Mean Squared Error/ Root Mean squared Error

2) Mean Absolute Error

3) R squared/ Adjusted R square

question 6

What is the difference between multiple and adjusted coefficient of determination

Adjusted R-squared adjusts the statistic based on the number of independent variables in the model.