We should always consider the ______ and ______ tradeoff in model training.

I. bias
II. objectivity
III. partiality
IV. variance
V. harmony

Correct Answer: I and IV

High Bias means the model is less than optimal (underfitting). A model with too much bias systematically ignores relevant details and is wrong in consistent ways.

High Variance mean the model is very sensitive to the sample used to build the model. That is, the error highly depends on the training set used and hence the variance of the error (evaluated across different cross-validation-folds) will extremely differ (overfitting). Such models tend to be wrong in inconsistent ways.