Re:Decoupled Neural Interfaces Using Synthetic Gradients
by signa11 on Tuesday August 30, 2016 @03:37AM
(#12388179)
> I can't believe I'm getting down-voted just because I'm not bullish on ANN.
probably it is happening because ANN's definitely do have some advantage over SVM's for modelling real world phenomenon.
specifically, ANN's are _parametric_, while SVM's are nonparametric in the sense that for an ANN, you have a bunch of hidden layers (of varying sizes) depending on the number of features, and a bias parameter. this is your model.
SVM's otoh (at least in the kernelized case), consist of set of support-vectors selected from a training set. which in worst case can be as large as the training set.
modelling real world phenomenon, for example optimal air-conditioning based on a large number of external inputs in a data center, are far more conducive in ANN's than SVM's. ANN's are afterall universal approximators. with SVM's you have to guess the kernel...
probably it is happening because ANN's definitely do have some advantage over SVM's for modelling real world phenomenon.
specifically, ANN's are _parametric_, while SVM's are nonparametric in the sense that for an ANN, you have a bunch of hidden layers (of varying sizes) depending on the number of features, and a bias parameter. this is your model.
SVM's otoh (at least in the kernelized case), consist of set of support-vectors selected from a training set. which in worst case can be as large as the training set.
modelling real world phenomenon, for example optimal air-conditioning based on a large number of external inputs in a data center, are far more conducive in ANN's than SVM's. ANN's are afterall universal approximators. with SVM's you have to guess the kernel...
edit-001 : see for example, this paper: http://deeplearning.net/wp-content/uploads/2013/03/dlsvm.pdf , where folks try their hands at deep-learning via SVM's.