1DGAN
A one dimensional generative adversarial network(GAN) inspired by https://machinelearningmastery.com/how-to-develop-a-generative-adversarial-network-for-a-1-dimensional-function-from-scratch-in-keras/
The GAN here attempts to learn to generate values that fit within a segment of sin(x) and achieves this quite quickly even through CPU training due to the low number of parameters in the neural networks.
I included a requirements file for use in conda.