|
|
|
|
|
|
by scribu
3628 days ago
|
|
|
It seems like you're talking about human-created models (e.g. a manually-constructed decision tree), whereas the paper's primary concern is machine-created models (e.g. the weights derived mechanically by a neural network). So the problem would be: how do you get the "modelers" (i.e. the machines) to be "honest about the flaws" of the models that they generated? |
|
|