This project is a feedforward neural network built entirely from scratch in vanilla JavaScript as a learning exercise. It is designed to solve the classic Iris flower classification problem, featuring a dynamic 3D visualization created with Three.js. This visualizer renders the network's structure and animates the training process in real-time, showing how weights, biases, and neuron activations change as the model learns from the data.
-
Notifications
You must be signed in to change notification settings - Fork 0
hijaz/iris
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
A vanilla javascript implementation of a feed forward neural network
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published