Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on When to assume neural networks can solve a problem.
"You should understand the problem well enough to list some potential solutions to test first to find the best model" and "it shouldn't be used for a problem that conventional programming can solve" like hard coding a symbolic rule.
https://joelgrus.com/2016/05/23/fizz-buzz-in-tensorflow/
"You should understand the problem well enough to list some potential solutions to test first to find the best model" and "it shouldn't be used for a problem that conventional programming can solve" like hard coding a symbolic rule.