News for hackers. Stuff that matters.
Re:Deep learning is creating computer systems we don't fully... by jimbokun on Wednesday July 13, 2016 @11:47AM (#12087114)
"the weights are such that the ANN computed this incorrect output for these inputs?"

Can we actually do this, for complex ANNs?

Re:Deep learning is creating computer systems we don't fully... by espadrine on Wednesday July 13, 2016 @12:52PM (#12087657)
Yes. The matrix is stored. In fact, there has been a number of visualization tools for neural nets to help track down which weights contribute to which results.

Additionally, the weights are constant in production, which makes analyzing production issues just a matter of logging the inputs and the outputs. Of course, for most convolutional nets, the inputs can get quite large (for example, a camera feed).