MathGroup Archive 2003

[Date Index] [Thread Index] [Author Index]

Search the Archive

Re: 3D plot of error function of neural network

  • To: mathgroup at smc.vnet.net
  • Subject: [mg42417] Re: 3D plot of error function of neural network
  • From: "AngleWyrm" <no_spam_anglewyrm at hotmail.com>
  • Date: Sat, 5 Jul 2003 03:11:02 -0400 (EDT)
  • References: <bdefm2$dl6$1@smc.vnet.net>
  • Sender: owner-wri-mathgroup at wolfram.com

"Bastian" <baspo at web.de> wrote in message news:bdefm2$dl6$1 at smc.vnet.net...
> Hello,
> I want to plot an example for an neural network error surface
> depending on two weights.

Ok, I surmize that x is one weight, and y is another weight, and z is a
single output. Given this scenario, what is the formula you are using to
calculate the output(z) from the two input weights (x,y) ?

outputWeight:= Sin[x y] ;     <-- just some example formula using x and y
Plot3D[ outputWeight, {x, -5, 5}, {y, -5, 5}]         <-- the change the x
and y ranges to suit you.

or if you are interested in a bird's eye view of the surface, you can use a
contour plot:
ContourPlot[ outputWeight, {x, -5, 5}, {y, -5, 5}];

It is my guess that your x and y ranges are probably floats in the range of
0.0 to 1.0.


  • Prev by Date: Re: 3D plot of error function of neural network
  • Next by Date: Re: A puzzle for Mathematica
  • Previous by thread: Re: 3D plot of error function of neural network
  • Next by thread: Re: 3D plot of error function of neural network