File Exchange

image thumbnail

Neural Network Symbolic expression

version 1.1 (2.87 KB) by

Prints out the symbolic expression of a Matlab Neural Network toolbox object



View License

Given a neural network object, this function returns the closed, symbolic, expression implemented by the network (as a string).

This allows you to use a neural network model without relying on the neural network toolbox.

Note I only implemented for feed forward nets (MLPs) and not all possible transfer functions are supported. However, it should be very straightforward to do this.


>> net = newff([-1 1; -1 1],[3 1]);
>> getNeuralNetExpression(net)

ans =

(2/(1+exp(-2*((2/(1+exp(-2*(x1*1.728941e+00 + x2*1.700224e+00 + -2.424871e+00)))-1)*-9.045580e-01 + (2/(1+exp(-2*(x1*-2.422662e+00 + x2*-1.034790e-01 + 000000)))-1)*-1.976229e-01 + (2/(1+exp(-2*(x1*2.044171e+00 + x2*1.304364e+00 + 2.424871e+00)))-1)*1.050105e+00 + 000000)))-1)


This function originates from the Surrogate Modeling (SUMO) Toolbox :

Comments and Ratings (6)

Is it possible to modify the code so I get the expression with symbolic coeffs ?

John Booker

Dirk Gorissen

surya: Sorry I havent read the comments here in a long time. But I dont really understand your question. Just use it as described. Create a neural network object and call getNeuralNetExpression..


surya (view profile)

sir tell me how to search in google as i have been doing it by
neural network in symbolic expres.. in many combinations


surya (view profile)

sir plz reply 2 me
i am working on the same topic could u help me plzz
my mail id is

john lancaster



Updated the license conform Mathworks' new policy

MATLAB Release
MATLAB 7.6 (R2008a)

Download apps, toolboxes, and other File Exchange content using Add-On Explorer in MATLAB.

» Watch video