6MACHINE LEARNING
The goal of machine learning is to train models to generate correct outputs when given previously unseen inputs. This is usually done by repeatedly presenting the model with a collection of known inputs and outputs until the model succeeds in properly assigning outputs to inputs, or learns.
In this chapter, we’ll explore randomness in machine learning by building two datasets for histology slides and images of handwritten digits. As we’ll learn, randomness is essential to building suitable machine learning datasets.
Next, we’ll explore randomness in neural networks—the driving force behind the AI revolution. We’ll restrict ourselves ...
Get The Art of Randomness 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.
