What is Bias?#

Bias is a gap between the predicted and actual value.
High bias means high gap and Low bias means low gap.
A model with a high bias pays little attention to the training dataset and it oversimplifies the model.
Which in turn leads to high error in both training and testing dataset.

What is Variance?#

It tells about how much scattered predicted values are. Model with high variance overfits in the training dataset and performs poorly in testing dataset to handle this scenario we can use regularization you can read about it here. Low variance means predicted values are together. And high variance means predicted values are away from each other.

Graphical illustration of bias and variance. Image Courtesy

And when there is low variance and high bias it is called as underfitted model.
When there is high variance and low bias it is called as overfitted model.

Types of Model. Image Courtesy

So, it is very important to find balance between the bias and variance which is called as Bias-Variance Trade off. So, the value of total error also decreases.

Model Complexity Vs Error. Image Courtesy

The END#