Learn about backpropagation and gradient descent by coding your own simple neural network from scratch in Python - no libraries, just fundamentals. Ideal for aspiring Machine Learning Engineers, Data Scientists, and AI Specialists.Coding neural networks from scratch using only PythonWhat backpropagation is and how it helps machines learnHow to break down complicated math into simple, doable stepsThe easiest way to understand gradients and why they matterWhat’s really happening when a machine makes predictionsHow to train a smarter model by adjusting tiny details in code
- Introduction
Introduction
Exercise: Meet Your Classmates and Instructor
Course Resources
- Neural Networks, Derivatives, Gradients, Chain Rule, and Gradient Descent
Introduction to Our Simple Neural Network
Why We Use Computational Graphs
Conducting the Forward Pass
Roadmap to Understanding Backpropagation
Derivatives Theory
Numerical Example of Derivatives
Partial Derivatives
Gradients
Understanding What Partial Derivatives Dо
Introduction to Backpropagation
(Optional) Chain Rule
Gradient Derivation of Mean Squared Error Loss Function
Visualizing the Loss Function and Understanding Gradients
Using the Chain Rule to See how w2 Affects the Final Loss
Backpropagation of w1
Introduction to Gradient Descent Visually
Gradient Descent
Understanding the Learning Rate (Alpha)
Moving in the Opposite Direction of the Gradient
Calculating Gradient Descent by Hand
Coding our Simple Neural Network Part 1
Coding our Simple Neural Network Part 2
Coding our Simple Neural Network Part 3
Coding our Simple Neural Network Part 4
Coding our Simple Neural Network Part 5
- Implementing Our Advanced Neural Network by Hand + Python
Introduction to Our Complex Neural Network
Conducting the Forward Pass
Getting Started with Backpropagation
Getting the Derivative of the Sigmoid Activation Function(Optional)
Implementing Backpropagation with the Chain Rule
Understanding How w3 Affects the Final Loss
Calculating Gradients for Z1
Understanding How w1 and w2 Affect the Loss
Implementing Gradient Descent by Hand
Coding our Advanced Neural Network Part (Implementing Forward Pass + Loss)
Coding our Advanced Neural Network Part 2 (Implement Backpropagation)
Coding our Advanced Neural Network Part 3 (Implement Gradient Descent)
Coding our Advanced Neural Network Part 4 (Training our Neural Network)
- Where To Go From Here?
Review This Byte!
