🧠
Neural Networks from Nothing
  • Neural Networks from Nothing
  • Preface
  • Chapter 1: Introduction to Neural Networks
  • Chapter 2: Python and NumPy Basics
  • Chapter 3: The Dataset: Generation and Analysis
  • Chapter 4: Weights Initialization in Neural Networks
  • Chapter 5: Defining the Model
  • Chapter 6: Loss Function: Measure of Prediction Accuracy
  • Chapter 7: Building the Training Loop
  • Chapter 8: Model Training and Evaluation
  • Chapter 9: Testing the Model
  • Chapter 10: Conclusion
  • Appendix
Powered by GitBook
On this page

Was this helpful?

Neural Networks from Nothing

A 10-chapter digital book teaching you the basics of machine learning from scratch! No linear algebra or calculus needed.

NextPreface

Last updated 1 year ago

Was this helpful?

Learn how to implement a very simple neural network (just one neuron)!

Along the way, you will gain a fundamental understanding of the math and logic behind how neural networks work. For instance, weight updates, biases, and gradients.

Please submit this one second Google Form to get instant access to the Colab notebook. Rather than using Google Analytics, this is how I track readership in a non-invasive way :)

It doesn't require email or name or literally anything!

Prerequisites:

  • basic knowledge of Python

  • middle school algebra

  • Google Colab account (free)

https://forms.gle/bZZ98vUSQir1e9Ee9
Page cover image