Re:What is the difference between deep learning and usual ma...
by Kip9000 on Sunday June 05, 2016 @04:08PM
(#11842852)
>MLPs can approximate any nonlinear function..
Theoritically yes. But the drama is when you have to actually do it. DNNs are not more tractable on their own, they are made feasible by current set of techniques.
>Is it that it is easier for humans to design the abstractions..
You could argue that activation maps generated in convolutional layers by the filters are feature engineering, as those filters are manually created. These are problem dependent, and we know more about the problem than the algos. That's why feature engineering hasn't gone away completely.
Theoritically yes. But the drama is when you have to actually do it. DNNs are not more tractable on their own, they are made feasible by current set of techniques.
>Is it that it is easier for humans to design the abstractions..
You could argue that activation maps generated in convolutional layers by the filters are feature engineering, as those filters are manually created. These are problem dependent, and we know more about the problem than the algos. That's why feature engineering hasn't gone away completely.