Mathematics Behind Backpropagation | Theory and Python Code
Unlock the Mathematics and Code Behind Neural Networks and Backpropagation
Created by Patrik Szepesi
Gain a deep understanding of how neural networks learn by exploring the mathematics behind backpropagation. Learn to apply concepts like gradients and gradient descent, and put theory into practice by coding your own neural network from scratch in Python.
Packt | Apr 2026 | 277 min
What You Will Learn
You will start by breaking down core mathematical concepts such as derivatives and gradients, then move on to practical coding exercises that reinforce each idea. By building and training a neural network step by step, you will bridge the gap between theory and real-world application, gaining both conceptual clarity and coding confidence.
Key Features
- Understand and apply derivatives, gradients, and the chain rule in neural networks
- Build and train a neural network from scratch using Python code for hands-on learning
- Visualize and optimize learning with computational graphs and gradient descent techniques
Target Audience
Perfect for data scientists, software developers, and aspiring machine learning engineers with a basic grasp of Python. If you want to truly understand how neural networks work under the hood and develop the skills to build and optimize models from scratch, this course is designed for you.
