One of the challenges with building a machine learning system is that there are so many things we could try, so many things we could change for example tuning hyperparameters. Whether we are tuning hyperparameters or trying out different ideas for learning algorithms, or just trying out different options for building a machine learning system. One thing that surely improves progress is to have a single real number evaluation metric that lets you quickly tell if the new thing just you tried is working better or worse than your last idea.
Bias and Variance are one of those concepts that are easily learned but difficult to master. In Machine Learning, when we want to optimize model prediction, it is very important to understand the parameters which describe errors and accuracy, In Machine Learning any model’s performance is based on its correct predictions and how well it is generalized on the training data(seen data), test data and validation data(unseen data) and real-time data.
Let’s see what this means:
In the first diagram, if we fit a straight line to the data, maybe we get a logistic regression fit to that. This…