Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Somebody should do a cost-benefit analysis of all this machine learning business. For instance, how much did this project cost and what did they get in return? I'm not suggesting it's not worth it, just curious to know how the numbers turn out.


Also, IIRC early neural net research covered this approach with Hannibal & Attila decades ago.

Edit: I guess there are some differences -- I think this is what I was remembering:

http://people.csail.mit.edu/brooks/papers/AIM-1091.pdf

...but maybe there was further work that is more closely related.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: