Build a Simple Neural Network & Learn Backpropagation

4h 34m 9s
English
Paid

Course description

Study backpropagation and gradient descent by writing a simple neural network from scratch in Python - without any libraries, just the basics. Perfect for future machine learning engineers, data specialists, and AI developers.

Read more about the course

What you will learn:

  • How to program neural networks from scratch using only Python
  • What backpropagation is and how it helps train models
  • How to break down complex mathematics into simple, executable steps
  • The simplest way to understand what gradients are and why they are important
  • What really happens when a machine makes predictions
  • How to train a smarter model by adjusting the smallest details in the code

This course unveils the essence of neural networks: mathematics and pure Python.

You will delve into the inner workings of backpropagation, gradient descent, and the mathematical foundations on which modern neural networks are built. No ready-made frameworks, no "black boxes" - just you, mathematics, and your code.

Step by step, you will manually build neural networks and implement them from scratch. From partial derivatives to updating weights - each concept will be dissected and implemented in code using Python (no libraries like PyTorch required!).

If you truly want to understand how machine learning works - and prove it by creating your own neural network - this course will be your starting point.

Watch Online

This is a demo lesson (10:00 remaining)

You can watch up to 10 minutes for free. Subscribe to unlock all 39 lessons in this course and access 10,000+ hours of premium content across all courses.

View Pricing
0:00
/
#1: Introduction

All Course Lessons (39)

#Lesson TitleDurationAccess
1
Introduction Demo
03:00
2
Introduction to Our Simple Neural Network
06:49
3
Why We Use Computational Graphs
06:20
4
Conducting the Forward Pass
06:56
5
Roadmap to Understanding Backpropagation
02:48
6
Derivatives Theory
04:28
7
Numerical Example of Derivatives
13:40
8
Partial Derivatives
08:02
9
Gradients
03:53
10
Understanding What Partial Derivatives DРѕ
10:14
11
Introduction to Backpropagation
05:01
12
(Optional) Chain Rule
07:33
13
Gradient Derivation of Mean Squared Error Loss Function
07:37
14
Visualizing the Loss Function and Understanding Gradients
11:39
15
Using the Chain Rule to See how w2 Affects the Final Loss
18:43
16
Backpropagation of w1
04:30
17
Introduction to Gradient Descent Visually
10:08
18
Gradient Descent
06:08
19
Understanding the Learning Rate (Alpha)
08:11
20
Moving in the Opposite Direction of the Gradient
05:31
21
Calculating Gradient Descent by Hand
08:48
22
Coding our Simple Neural Network Part 1
04:24
23
Coding our Simple Neural Network Part 2
07:17
24
Coding our Simple Neural Network Part 3
06:32
25
Coding our Simple Neural Network Part 4
05:01
26
Coding our Simple Neural Network Part 5
05:23
27
Introduction to Our Complex Neural Network
05:30
28
Conducting the Forward Pass
04:25
29
Getting Started with Backpropagation
04:52
30
Getting the Derivative of the Sigmoid Activation Function(Optional)
07:43
31
Implementing Backpropagation with the Chain Rule
04:55
32
Understanding How w3 Affects the Final Loss
06:10
33
Calculating Gradients for Z1
07:43
34
Understanding How w1 and w2 Affect the Loss
04:53
35
Implementing Gradient Descent by Hand
08:29
36
Coding our Advanced Neural Network Part (Implementing Forward Pass + Loss)
06:51
37
Coding our Advanced Neural Network Part 2 (Implement Backpropagation)
10:11
38
Coding our Advanced Neural Network Part 3 (Implement Gradient Descent)
05:35
39
Coding our Advanced Neural Network Part 4 (Training our Neural Network)
08:16

Unlock unlimited learning

Get instant access to all 38 lessons in this course, plus thousands of other premium courses. One subscription, unlimited knowledge.

Learn more about subscription

Comments

0 comments

Want to join the conversation?

Sign in to comment

Similar courses

RAG for Real-World AI Applications

RAG for Real-World AI Applications

Sources: vueschool.io, Justin Schroeder, Daniel Kelly, Garrison Snelling
Study the RAG approach to enhance AI with your own data. Learn about vectors, embeddings, and integration. Apply the approach in real projects.
26 minutes 55 seconds
Predictive Analytics & Machine Learning

Predictive Analytics & Machine Learning

Sources: LunarTech
Predictive analytics and machine learning is a course that will help you master key concepts and practical skills in data forecasting...
55 minutes 15 seconds
RAG (Retrieval)

RAG (Retrieval)

Sources: Mckay Wrigley (takeoff)
Study the key principles of developing Retrieval-Augmented Generation (RAG) systems and the application of advanced search methods to improve the performance...
4 hours 33 minutes 19 seconds
Turbo Mode: Optimizing Productivity with AI Tools and Agents

Turbo Mode: Optimizing Productivity with AI Tools and Agents

Sources: vueschool.io, Justin Schroeder, Daniel Kelly, Garrison Snelling
Find out how to create custom AI agents and develop universal rules to enhance your productivity and address all aspects of the project.
1 hour 2 minutes 46 seconds
AI Engineering: Customizing LLMs for Business (Fine-Tuning LLMs with QLoRA & AWS)

AI Engineering: Customizing LLMs for Business (Fine-Tuning LLMs with QLoRA & AWS)

Sources: zerotomastery.io
Master an in-demand skill that companies are looking for: the development and implementation of custom LLMs. In the course, you will learn how to fine-tune open
7 hours 12 minutes 10 seconds