I found the following assertion in a neural networks FAQ:

Radial networks typically have only one hidden layer, but it can be useful to include a linear layer for dimensionality reduction or oblique rotation before the RBF layer

But I could not find any "formal" reference (published works) showing it. I found some papers describing EBFNN's, but they implement full covariance matrices on the RBF units. I could not find anything about this approach with an extra linear layer before the RBF layer. The theory is ok for me, it makes sense and works. What I need is any published work with this information. Is there one?

  • $\begingroup$ 1. Why do you need a published work? 2. Often these kinds of observations are made based upon experience so it's even possible it might just be folklore. $\endgroup$ – D.W. Aug 3 '15 at 17:34
  • $\begingroup$ I want to use it in my own work and didn't want to leave it without any real reference. If I don't reference anything, it may have been published before and I fail to cite it. Other option would be to reference the FAQ itself, but I think some journals may see it as a bad practice (I really don't know). $\endgroup$ – rcpinto Aug 3 '15 at 17:42

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.