This is related to confusing signal with noise.
THE BIAS-VARIANCE TRADE-OFF
– Bias: distance of the results to the target.
– Variance: the spread of the results
OVERFITTING VS UNDERFITTING
– Overfitting: The model get more complex and fits too much to the noise from the data. This results in low error on training set, but high error on new data, test/validation sets.
– Underfitting: Model too simple does not capture the underlying trend of the data and does not fit the data well enough. Low variance but high bias.