Skip to content
Creating a simple neural network in Python with one input layer (3 inputs) and one output neuron.
Python
Branch: master
Clone or download
jonasbostoen Update main.py
fixed type bug
Latest commit 985d829 Aug 13, 2018
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
README.md Update README.md Mar 29, 2018
main.py Update main.py Aug 13, 2018
outputs.txt Create outputs.txt Mar 27, 2018
requirements.txt Create requirements.txt Apr 1, 2018
training_version.py Rename simple_version.py to training_version.py Mar 29, 2018

README.md

Simple Neural Network

Creating a simple neural network in Python with one input layer (3 inputs) and one output neuron. A neural network with no hidden layers is called a perceptron. In the training_version.py I train the neural network in the clearest way possible, but it's not really useable. The outputs of the training can be found in outputs.txt . neural_network.py is an object and can be used by giving in different inputs.

Thanks to Milo Spencer-Harber for this: https://medium.com/technology-invention-and-more/how-to-build-a-simple-neural-network-in-9-lines-of-python-code-cc8f23647ca1

And to Andrew Trask for this: https://iamtrask.github.io/2015/07/12/basic-python-network/

What does it do?

The neural_net.py tries to predict the output given 3 binary inputs. If the first input is 1, the output should be one. Otherwise the output should be 0.

You can’t perform that action at this time.