>I think both you and the author of the article are making the same mistake here. Maybe? >If you have a nonlinear function f on a vector space, there's no reason why an orthogonal basis for that space will give a better…
This book is a good practical introduction that walks you through the basic ideas as you develop some basic functionality. http://neuralnetworksanddeeplearning.com/ I'm often pretty skeptical of e-books and self…
>I think both you and the author of the article are making the same mistake here. Maybe? >If you have a nonlinear function f on a vector space, there's no reason why an orthogonal basis for that space will give a better…
This book is a good practical introduction that walks you through the basic ideas as you develop some basic functionality. http://neuralnetworksanddeeplearning.com/ I'm often pretty skeptical of e-books and self…