Chapter 7
Introducing Neural Networks and Deep Learning
IN THIS CHAPTER
Exploring the development of neural networks
Looking at perceptrons, multilayer perceptrons (MLPs), and deep learning
Managing variables with scope
Demonstrating deep learning in a TensorFlow application
This chapter explains how neural networks operate and how to use them to analyze data in TensorFlow applications.
From Neurons to Perceptrons
For many, the topic of neural networks conjures visions of artificial brains, omniscient computers that predict the future, and other fixtures of science fiction. But practitioners of machine learning take a more down-to-earth view: Neural networks are useful computational tools, but they’re not ideal for every application, and they’re never completely reliable.
Biology inspired the development of neural networks, but their essential operation is statistical in nature. Neural networks analyze data to discover mathematical relationships between inputs and outputs. They should only be used as a last resort — if you already have clear rules that relate outputs to input data, ...
Get TensorFlow For Dummies 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.
