Function mapping using a neural network with a single hidden layer
This repository contains code for my experimentation with the expressivity of neural networks with a single hidden layer.
Note: To make the input data more realistic I have added Gaussian noise with mean=0 and standard deviation of 0.1
- Python 2.7+ or 3.5+.
- Tensorflow and its requirements. I use the pip tensorflow-gpu==1.6.0
- NumPy. The pip should work.
- Matplotlib. The pip should work.
python neural_net_funcmappimg.py func_name
func_name can be sine,cube,square