Class Central is learner-supported. When you buy through links on our site, we may earn an affiliate commission.

YouTube

How to Create a Neural Network and Train It to Identify Doodles

Sebastian Lague via YouTube

Start learning Write review
Noble Desktop Ad

Live Online Classes in Design, Coding & AI — Small Classes, Free Retakes

Learn More → Coursera Ad

Learn AI, Data Science & Business — Earn Certificates That Get You Hired

Learn More →

Overview

Google, IBM & Meta Certificates – 40% Off
One Coursera Plus subscription covers most Professional Certificates on Coursera.
Unlock All Certificates
This course builds a neural network from scratch in C# and trains it to recognize handwritten digits, clothing images, doodles, and other images. It explains weights, biases, hidden layers, activation functions, gradient descent, calculus, and backpropagation through practical implementation.

Syllabus

Introduction
The decision boundary
Weights
Biases
Hidden layers
Programming the network
Activation functions
Cost
Gradient descent example
The cost landscape
Programming gradient descent
It's learning! slowly
Calculus example
The chain rule
Some partial derivatives
Backpropagation
Digit recognition
Drawing our own digits
Fashion
Doodles
The final challenge

Taught by

Sebastian Lague

Reviews

Start your review of How to Create a Neural Network and Train It to Identify Doodles

Start learning

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Sign up for free
Someone learning on their laptop while sitting on the floor.