Chapter 3. Introduction to neural prediction: forward propagation
In this chapter
- A simple network making a prediction
- What is a neural network, and what does it do?
- Making a prediction with multiple inputs
- Making a prediction with multiple outputs
- Making a prediction with multiple inputs and outputs
- Predicting on predictions
“I try not to get involved in the business of prediction. It’s a uick way to look like an idiot.”
Warren Ellis comic-book writer, novelist, and screenwriter
In the previous chapter, you learned about the paradigm predict, compare, learn. In this chapter, we’ll dive deep into the first step: predict. You may remember that the predict step looks a lot like this:
In this chapter, you’ll learn more about what these three different parts of a neural network prediction look like under the hood. Let’s start with the first one: the data. In your first neural network, you’re going to predict one datapoint at a time, like so:
Later, you’ll find that the number of datapoints you process at a time has a significant impact on what a network looks like. You might be wondering, “How do I choose how many datapoints to propagate at a time?” The answer is based on whether you think the neural network can be accurate with the data you give it.