Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Building a simple neural net in Java. Parent comment
NN solutions end up being discontinuous stacks of linear regressions.
So it's not a bad place to start in explaining NNs. ReLU NN models are piece-wise linear.
There are no comments on this comment yet.
NN solutions end up being discontinuous stacks of linear regressions.
So it's not a bad place to start in explaining NNs. ReLU NN models are piece-wise linear.