One of the many impressive things about neural networks is how well the same
basic algorithm can adapt to very different kinds of problems. I’ve used the
same framework, Char-rnn [https://github.com/karpathy/char-rnn], to produce
things like recipes
[http://lewisandquark.tumblr.com/post/140219420017/the-silicon-gourmet-training-a-neural-network-to]
, Dr. Who
![Sports teams designed by neural network](/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)