|
|
--- |
|
|
language: |
|
|
- en |
|
|
tags: |
|
|
- neural-network |
|
|
- pytorch |
|
|
- fractal |
|
|
- mandelbrot |
|
|
- function-learning |
|
|
- math |
|
|
--- |
|
|
Neural Networks can learn any function, even capturing fractal level details. |
|
|
|
|
|
Approximated the #Mandelbrot set, a classic chaotic fractal, an infinitely complex boundary generated by a simple formula in the complex plane. Every zoom reveals more intricate detail, forever. |
|
|
|
|
|
In this small-scale project, I trained a neural network to learn the fractal shape from pixel coordinates using PyTorch, NumPy, and Matplotlib. This isn’t curve-fitting. This is pure function learning. |
|
|
|
|
|
- Added positional encodings to represent spatial patterns |
|
|
- Increasing epochs and depth for better generalization |
|
|
- And tuning resolution + loss functions |
|
|
|
|
|
The model approximated the Mandelbrot set with stunning accuracy, no image inputs, just math. |
|
|
|
