AI Engineering Degree Practice Exam

The formula for calculating the Relative Absolute Error (RAE) is expressed as the sum of the absolute differences between actual and predicted values, divided by the sum of the absolute differences between the actual values and their mean. This formula provides a way to evaluate the accuracy of a predictive model relative to a simple model that uses the mean of the actual values. Using this formula allows one to gauge how well the predictive model is performing in comparison to a baseline, which is the mean of the actual values. It highlights how much error is incurred by the model in the context of the overall variability present in the actual data. When the RAE is low, it indicates that the model's predictions are close to the actual values as compared to just using the mean. This understanding makes it easier to assess model performance, especially in cases where one may be dealing with different scales of measurement or needs a normalized error metric. The other choices do not accurately capture the computation of RAE. For instance, while the second option discusses a form of error calculation, it does not involve relative error concerning the mean, which is essential for RAE. The third and fourth choices introduce different calculations that do not correspond to the definition of RAE, focusing either on squared errors or a