[mlpack] L2 Regularization for NN
Marcus Edel
marcus.edel at fu-berlin.de
Thu Jan 18 08:57:20 EST 2018
Hello Eugene,
Currently, it's not possible to apply penalties on layer parameters or layer
activity during the optimization process. However, it should be straightforward
to implement a layer that can apply penalties. Another option would be to
implement it as a decay policy so that it can be used inside the optimizer.
Thanks,
Marcus
> On 17. Jan 2018, at 22:44, Evgeny Freyman <evg.freyman at gmail.com> wrote:
>
> Hi. Could anybody suggest where to look if I want to add L2 regularization parameter on coefficients of FFN. Is it possible in current API ?
>
> All the best
> Eugene Freyman
> _______________________________________________
> mlpack mailing list
> mlpack at lists.mlpack.org
> http://knife.lugatgt.org/cgi-bin/mailman/listinfo/mlpack
More information about the mlpack
mailing list