how to use neural network as fitness function for GA?

i have created a neural network using neural network toolbox. i wanted to use this network as a fitness function in GA toolbox. can you please tell me how to do this.

Answer 1

[Greg Heath]

I have never heard of using a neural network as a fitness function. This wording implies that the network is fully trained and implements the estimate of a nonnegative function of the inputs that will be minimized for one or more optimal subsets of inputs.

Or are you just trying to use GA to design a net by finding one of the optimal sets of weights?

If so, the NNTBX does not have that option. You will have to design your own code which, ideally, will include GA functions of other Toolboxes. To find these type

 lookfor genetic

and

 ver

Hope this helps.

Thank you for formally accepting my answer

Greg

[abhishek r]

sir, the problem we are having is that we lack a fitness function for our set of data. we have conducted an experiment and we have got a set of data based on which we have trained a network. now we have to find the optimum value of the experiment using GA. but we don't have an objective function to provide the GA for optimization. (1) so is there any way by which we can create an equation from this trained network to be given to the GA? (2) since the network is capable of producing outputs for certain inputs, is there any chance we could use this trained network as the fitness function.

[Greg Heath]

Too vague. Details needed. What kind of data? What are the inputs? What are the outputs ? size(input)? size(target)? What kind of network? What do you mean by optimum value?

[abhishek r]

We have done an experiment regarding weight of a system. We have to optimise (find the minimum) the weight of the system involved. The experiment involves three parameters. The size of input is 3x79 and the size of output is 1x79. Using these data we have created a feedforward backpropogation with 10 neurons(1 hidden layer). As our problem doesnt have an objective function we need this trained network to act as a fitness function in Genetic Algorithm for optimisation within the specified range of our input.

[Greg Heath]

Well, what are the three parameters and what is the output?

Didn't I ask thiese questions before???

[Fazal Ibrahim]

I am also facing similiar problem..

My input parameters are heat input, clamping location and welding speed..I want to minimize residual stress(output)