Taylor Michael, Koning Mark. Machine Learning with Neural Networks

Blue Windmill Media, 2017. — 248 p.Neural networks have made a gigantic comeback in the last few decades and you likely make use of them everyday without realizing it, but what exactly is a neural network? What is it used for and how does it fit within the broader arena of machine learning?On a high level, a network learns just like we do, through trial and error. This is true regardless if the network is supervised, unsupervised, or semi-supervised. Once we dig a bit deeper though, we discover that a handful of mathematical functions play a major role in the trial and error process. It also becomes clear that a grasp of the underlying mathematics helps clarify how a network learns.You will learn to build a simple neural network using all the concepts and functions we learned in the previous few chapters. Our example will be basic but hopefully very intuitive. Many examples available online are either hopelessly abstract or make use of the same data sets, which can be repetitive. Our goal is to be crystal clear and engaging, but with a touch of fun and uniqueness. This section contains the following eight chapters.What You’ll Find Inside
Don’t Waste Your Time
Neural Networks
What Is A Neural Network?
The Math of Neural Networks: Overview
The Math Of Neural Networks: Introduction
Basic Terminology And Notation
Pre-Stage: Creating the Network
Forward Propagation
The Mathematical Functions Used 6: Understanding Matrices
Fitting it All Together: Review
Calculating The Total Error
Calculating The Total Error
Calculating The Gradients
The Mathematical Functions Used
Why Gradients Are Important
Partial Derivative of Output Layer Weights
Partial Derivative of Output Layer Bias Weights
Partial Derivative of Hidden Layer Weights
Partial Derivative of Hidden Layer Bias Weights
Fitting It All Together: Review
Checking The Gradients
Numerical Estimation
Discovering The Formula
Calculating The Numerical Estimation
Fitting it All Together: Review
Updating The Weights
What is Gradient Descent?
Methods of Gradient Descent
Updating the Weights
Fitting it All Together: Review
Constructing a Network: Hands on Example
Defining the Scenario
Pre-Stage: Network Structure
Stage 1: Running Data Through the Network
Stage 2: Calculating the Total Error
Stage 3: Calculating the Gradients
Stage 4: Gradient Checking
Stage 5: Updating the Weights
Wrapping it All Up: Final Review
Building Neural Networks in Python
The Tools You’ll Need
Tensorflow: A Very Brief Overview
Tensorflow and Neural Networks: 5 Steps
Neural Network: Distinguish Handwriting
Neural Network: Classify Images
The History of Neural Networks
A Brief History of Neural Networks
Additional Resources
Extended Definitions
Text Editors and Libraries