I’ve trained this open-source neural network
[http://t.umblr.com/redirect?z=https%3A%2F%2Fgithub.com%2Fkarpathy%2Fchar-rnn&t=YTE5MjZhYmIzNTQwODIwOGQwNjE1MzY4ZDBkOWY2YTdhNjRhNGJlYSx3dEtLQjlwOQ%3D%3D&b=t%3AIinBpZOgiMHH_bphj7hrOQ&p=http%3A%2F%2Flewisandquark.tumblr.com%2Fpost%2F159117179212%2Fthe-neural-network-generated-pickup-lines-that-are&m=1]
framework on a variety of datasets,
![The neural network writes the episode list for next season’s Dr. Who](/content/images/size/w795/image/fetch/w_256-c_limit-f_auto-q_auto:good-fl_progressive:steep/https-3A-2F-2Fbucketeer-e05bbc84-baa3-437e-9518-adb32be77984.s3.amazonaws.com-2Fpublic-2Fimages-2Fa2c7c912-2468-4adf-b37c-57d1339a2153_489x489.png)