Looking for a career upgrade & a better salary? We can help, Choose from our no 1 ranked top programmes. 25k+ career transitions with 400 + top corporate companies. Exclusive for working professionals: https://glacad.me/3eO7rXR Get your free certificate of completion for the Analysis of Variance course, Register Now: https://glacad.me/32LaxJT In simple words, bias means how far you have come in predicting the desired value from your actual value. It is an approach that can ultimately make or break the model in favor or against your idea. A straightforward example can be: When we talk about the famous linear regression model, we quantify the relationship between X and Y variable as linear; on the contrary, in reality, the relationship might not be perfectly linear as we had read. Variance is the reverse of bias. It is called the variance when your model performs exceptionally well on the training dataset yet fails to live up to the same standards when running it on an entirely new dataset. In simple words, your model conveys to you that the predicted values are very scattered from the actual values. This concept is similar to the overfitting of the model on the dataset, also called the difference between the model fits when used on different datasets. 01:25 – Agenda 01:56 – Introduction 04:35 – Bias and Variance in Machine Learning 07:42 – Difference between Bias and Variance 08:15 – Bias vs Variance 13:14 – Bias Variance Trade-Off 18:03 – Bias and Variance In Machine Learning 18:34 [More]