9 Overfitting and Underfitting
Whether we’re a person or a computer, learning general rules about a subject from a finite set of examples is a tough challenge. If we don’t pay enough attention to the details of the examples, our rules will be too general to be of much use when we’re considering new data. On the other hand, if we pay too much attention to the details in the examples, our rules will be too specific, and again we’ll do a bad job at evaluating new data.
These phenomena are respectively called underfitting and overfitting. The more common and troublesome problem of the two is overfitting, and if unchecked, it can leave us with ...
Get Deep Learning now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
