Now, let's learn about MNIST digits. In this section, we'll look at the ImageData notebook that I've prepared to help us understand how to deal with image data; downloading and getting the MNIST digits; looking at images as raw numbers; and then finally, visualizing the actual images based on this numeric data.

The code we're going to be working with is contained in an IPython Notebook. This is the way we've set up our container, so you're going to be running your container like we mentioned at the end of the setting up your Machine Learning Toolkit. I've also prepared an ImageData IPython Notebook that we're going to be working with. We will start off by importing all the necessary packages, and we're going to, turn on Matplotlib in order to automatically plot. This means that when we show an image, we don't have...

Now that we've learned a bit about MNIST digits, we're going to take the time to look at a tensor, and what a tensor is. We're going to be looking at a NumPy of multidimensional arrays. Multidimensional arrays are also called tensors. The math vocabulary can be mildly overwhelming, but we're going to show you that it's a lot simpler than you might think. Then, we'll look at tensor shape. Tensor shape is really the number of dimensions, or, in terms of arrays, the number of different indices that you would use to access them. And then finally, we're going to look at datatypes. The tensors, or multidimensional arrays, can hold a wide array of different datatypes, and we'll explain some of the differences.

Let's start with the basics. The most basic tensor you can imagine is a one tensor, which...

In the previous section, we learned a bit about what a tensor is. Now, we're going to use that knowledge to prepare image data as tensors for machine learning. First, we'll ask a question: why are we working with data in floating points? Then, we will learn the difference between samples and the data points at the end of them. Finally, we will normalize the data for use in machine learning.

So, why a floating point? Well, the real reason is that machine learning is fundamentally a math optimization problem, and when we're working with floating points, the computer is trying to optimize a series of mathematical relationships to find learned functions that can then predict outputs. So, preparing our data for machine learning does involve reformatting normal binary data, such as an image, into a series of floating point numbers, which isn...

In the previous section, we looked at turning images into tensors for machine learning, and in this section, we will look at turning the output values, the categories, into tensors for machine learning.

We will cover output classes, what it means to make a discrete prediction, the concept of one-hot encoding; and then we'll visualize what one-hot encoding looks like as an image, and then we'll recap with a data preparation cookbook, which you should use to be able to deal with all kinds of image data for machine learning.

But for now, let's talk about output. When we're talking about digits, there's 0 through 9, so there's ten different classes, and not classes in the object-oriented sense, but classes in the label sense. Now, with these labels being from 0 to 9 as individual digits, the predictions we want to make...

In this chapter, we learned about the MNIST digits, and how to acquire them; how tensors are really just multidimensional arrays; how we can encode image data as a tensor; how we can encode categorical or classification data as a tensor; and then we had a quick review and a cookbook approach to think about dimensions and tensors to get data prepared for machine learning.

Now that we've learned how to set up our input and output data for machine learning, we're going to move on to the next chapter, where we will create a Classical Neural Network (CNN).