Tradeoffs
When training a model, there is always a tradeoff between the model having bias and variance. When a model is suffering from high bias, it means that it is UNDER-fitting to the data and is not able to make precise predictions.
Conversely, if the model is suffering from high variance, it means that it is now OVER-fitting to the data which makes it hard for the model to make predictions for data that has not been yet observed.
When training a model, it is important to find the right hyper-parameters that have the optimal balance between bias and variance.
