4WORKING WITH DATA
Developing a proper dataset is the single most important part of building a successful machine learning model. Machine learning models live and die by the phrase “garbage in, garbage out.” As you saw in Chapter 1, the model uses the training data to configure itself to the problem. If the training data is not a good representation of the data the model will receive when it is used, we can’t expect our model to perform well. In this chapter, we’ll learn how to create a good dataset that represents the data the model will encounter in the wild.
Classes and Labels
In this book, we’re exploring classification: we’re building models ...
Get Practical 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.
