A Perceptron: a one-neuron neural network
We calculate the final price from your selected file. You review and accept it before payment.
Saved on this device.
This Perceptron provides a hands-on demonstration of deep learning and neural nets: how they're trained and used.
- Rating
- 0 / 5
- Likes
- 0
- Downloads
- 2
- Makes
- 0
- Views
- 51
- Reviews
- 0
Updated at source:
Model information
- Source
- Printables
- Category
- Engineering
- License
- Creative Commons — Attribution
The Perceptron is a simple one-neuron neural network, and the wonderful thing about it is that it provides a hands-on demonstration of how deep learning and neural nets work - how they're trained and how that are used to do inference.
In this video tutorial, I use this device to illustrate the four things you need to know to understand deep learning and neural nets. It was inspired by this other video tutorial from Welch Labs. So watch these videos, build this device, and then use it to teach someone (or yourself) about neural nets.
The build is easy, but besides the 3D printer, you'll need a soldering iron. I've provided a full build guide. All of the files you need are in the GitHub repository. The 3D model files are here on Printables (since that's required), but better to get everything from the repository, since that's what I'll keep up date with any improvements I make.