Three bad recipes generated by neural network (2017)
aiweirdness.com
Three bad recipes generated by neural network (2017)
1–10 of 16 posts
Re: Three bad recipes generated by neural network (2017)
#2It failed at making recipes but it excels at comedy!
Re: Three bad recipes generated by neural network (2017)
#3If you put whole recipes into the neural network, of course it won't work. You need to separate the parts. One neural network for ingredients, and a separate one for "instructions".
Then you feed the output of the first network into the second to get a set of preparations that actually prepare the chosen ingredients.
Re: Three bad recipes generated by neural network (2017)
#4It failed at making recipes but it excels at comedy!
apparently randomness is important factor in comedy, just like somewhat funny memes created by neural network https://news.ycombinator.com/item?id=17302917
maybe joke-generation is actual future of AI?
Re: Three bad recipes generated by neural network (2017)
#5_Highly_, highly related: https://gist.github.com/nylki/1efbaa36635956d35bcc
I tried condensing it a couple years ago ( https://news.ycombinator.com/item?id=14376816 - I was i336_ then), but I think the original is worth slowly reading through.
There are some definite gems in there that will most definitely cheer you up at the very least.
Re: Three bad recipes generated by neural network (2017)
#6It failed at making recipes but it excels at comedy!
Re: Three bad recipes generated by neural network (2017)
#7It failed at making recipes but it excels at comedy!
apparently randomness is important factor in comedy, just like somewhat funny memes created by neural network https://news.ycombinator.com/item?id=17302917 maybe joke-generation is actual future of AI?
Perhaps randomness is a shortcut to absurdity, but good comedy is rarely random. (Is it ever? Honest question.)
Re: Three bad recipes generated by neural network (2017)
#8Related:
Awesome visual essay about using algorithms to generate (bad) cookie recipes
https://pudding.cool/2018/05/cookies/
Re: Three bad recipes generated by neural network (2017)
#9If you put whole recipes into the neural network, of course it won't work. You need to separate the parts. One neural network for ingredients, and a separate one for "instructions". Then you feed the output of the first network into the second to get a set of preparations that actually prepare the chosen ingredients.
What about your solution makes it right?
Re: Three bad recipes generated by neural network (2017)
#10What I get from this is that neural networks really have no idea what they are talking about (which of course is no news). How could they? Is a feature more important or relevant than another just because of its frequency?
People look at the output of neural networks and when they work they say - of course they do. And when they don't they rationalize it with "your model was wrong from the start".
(This is similar to how Alpha-Zero "discovered" the optimal chess openings. Of course it did, it was bound to find them by the rules of chess).