I’m training a neural network to generate recipes
[http://lewisandquark.tumblr.com/post/140219420017/the-silicon-gourmet-training-a-neural-network-to]
based on a database of about 30,000 examples, using the open-source char-rnn
[http://t.umblr.com/redirect?z=https%3A%2F%2Fgithub.com%2Fkarpathy%2Fchar-rnn&t=MjEyMTcxNjk0MWYyZGNmZGRkMjFjNDc3YWM2MjMyMDAwMTY1OTAxNixzVTRKT1VLRw%3D%3D&b=t%
![Bad recipe ideas from the 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)