Level 4: Neural Network Basics:
Covering Gradient Descent, Activation Functions,
Backpropagation, and the Fundamentals of Deep Learning.
Math & Python Textbook Series 8
“Curiosity about mathematics,
the foundation of everything in the AI era.”
Two free downloadable files : Hands-On Data Analysis with Python
Efficient learning with Colab note files linked to this book.
Beginner-friendly Python code explained step-by-step.
FilesStart Instantly in Your Browser—No Setup!
Contents:
Chapter 1 What Is Deep Learning?
Chapter 2 Building One Neuron: Input, Weight, and Bias
Chapter 3 Prediction and Error: How Far Off Is the Model?
Chapter 4 Loss Function: Expressing the Goal of Learning as a Number
Chapter 5 Adjusting the Weight Little by Little: The First Step of Learning
Chapter 6 Introduction to the Derivative: Knowing the Direction of Change
Chapter 7 Gradient Descent: How a Neural Network Learns
Chapter 8 Learning from Multiple Data Points
Chapter 9 Activation Functions: Bending a Straight Relationship
Chapter 10 Handling Multiple Inputs: Data as a Vector
Chapter 11 Neurons Side by Side: The Idea of a Layer
Chapter 12 Building a Multi-Layer Neural Network
Chapter 13 The Idea of Backpropagation: Sending the Error Back
Chapter 14 Neural Networks for Classification
Chapter 15 First Steps with Image Data
Chapter 16 Introduction to Convolutional Neural Networks
Chapter 17 Stabilizing Deep Learning Training
Chapter 18 A Hands-On Project: Building a Small Image Classifier
Appendix A NumPy Mini-Dictionary
Appendix B Neural Network Terms Mini-Dictionary
Appendix C The Math Used in Deep Learning
Appendix D The Project Template
Purchase site (English version)：Some sites only offer the digital version.
US (United States)
UK (United Kingdom)
DE (Deutschland)
FR (France)
ES (Spain)
IT (Italy)
NL (Nederland)
JP (Japan)
BR (Brasil)
CA (Canada)
MX (Mexico)
AU (Australia)
IN (India)