[mlpack-git] [mlpack] Create a function to visualize the features learned by sparse autoencoder (#465)

[Ryan Curtin]

> +        reshapeMat /= max;
> +      }
> +      output.submat(i*(offset), j*(offset),
> +                    i*(offset) + squareRows - 1,
> +                    j*(offset) + squareRows - 1) = reshapeMat;
> +      ++k;
> +    }
> +  }
> +}
> +
> +}
> +
> +void MaximalInputs(arma::mat const &parameters, arma::mat &output)
> +{
> +  //take the encoder part of the paramters
> +  arma::mat paramTemp = parameters.submat(0, 0, (parameters.n_rows-1)/2-1, parameters.n_cols-2);

If you did transpose the parameters, here would be the place to do it (just add `.t()` to the end of the expression).  I don't think it's reasonable to avoid a copy here, since you're subtracting the mean from `paramTemp`.

---
Reply to this email directly or view it on GitHub:
https://github.com/mlpack/mlpack/pull/465/files#r43119655
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://mailman.cc.gatech.edu/pipermail/mlpack-git/attachments/20151027/ce35b02f/attachment.html>