For fun ways in which NN classifiers reliably fail, google up adversarial inputs :-)
Example
Rubbish in, rubbish out—right?
No, not quite. It’s more like “let us poke around this NN and we’ll be able to craft inputs which look like one thing to a human and a completely different thing to the NN, and the NN is very sure of it”.
For fun ways in which NN classifiers reliably fail, google up adversarial inputs :-)
Example
Rubbish in, rubbish out—right?
No, not quite. It’s more like “let us poke around this NN and we’ll be able to craft inputs which look like one thing to a human and a completely different thing to the NN, and the NN is very sure of it”.