|
|
|
|
|
|
by throw_away_777
3325 days ago
|
|
|
The deep learning buzz-word applies to models which learn feature interactions in a fairly complicated manner. While it is possible to explain what a model is doing, the model is a black-box in the sense that without a computer you could not develop the model. The model is making a lot of decisions, and explaining why all those choices are made is not really feasible. In contrast, I could create a linear model by hand easily, it just won't be as good at complicated predictions. However I think the stigma against black-boxes is undeserved. The human brain is a black-box and no one argues against using it. |
|
|
Well, nobody's against using the brain, but the current trend in most subject domains is to avoid overrelying on intuition, and checking and supporting the conclusions using structured thinking methods, i.e. logic.
That is, deep learning is an intuition, and you have to have a high-level explanatory/verification mechanism that would support or reject the answer.