how to get objective function in neural network

1 次查看（过去 30 天）
prem kumar
prem kumar 2015-3-25
评论： prem kumar 2015-3-27
my question:
i have five inputs A B C D E and two outputs X Y. [A B C D E] are in the form of numerical data that is [ 115 47 21 3 4; 115 47 21 3 5; 115 47 21 3 6; 115 47 21 4 3; .............n27]. this 27 experiments conducted based on orthogonal array form. the outputs are [X y] is [ 3.41 6.24 3.25 6.1 2.94 5.14 .........n27].
i have to form neural network for these data after successful training i have to predict the unknown data accurately. after training the neural network its possible to get weight and biases value. till now i complete my neural network training in matlab application tool box i.e.. nntool.
in this i separate 22 data for training 5 data for testing. i used 2 hidden layer and 6 hidden neuron. my network is based on back propagation neural network with sigmoid and pure linear transfer function. i set the training epoch as 1000 and max fail is 6.
whether its correct or not? but after training the regression curve are quite better. and also after training is achieved my MSEis 0.00092.then i predicted the remaining 5 data, and the out put of those data are quite match with that my experimental data. how to fix the mse 0.0000001?.
whether my work is correct?. if correct means using the weights and biases value how to form an objective function in this trained neural network. because optimize this objective function with genetic algorithm. this works seams to be a hybrid of neural network with genetic algorithm.
whether its possible? if means how i do ? how i get the objective function? my work is purely on mechanical domain.
plz help me ...

请先登录，再回答此问题。

采纳的回答

Greg Heath
Greg Heath 2015-3-25
编辑：Greg Heath 2015-3-25
I think you are making the problem harder than it is. For example, neither a second hidden layer nor a genetic solution is warranted. Genetic solutions are not supported in the NNToolbox and such a solution may take orders of magnitude longer than straightforward backpropagation via trainlm.
The documentation for regression is obtained via help fitnet doc fitnet
Also see my posts on FITNET regression in the NEWSGROUPand ANSWERS. Search on
greg fitnet
greg fitnet tutorial
The latest was posted in the NEWSGROUP an hour or so ago.
Hope this helps.
Thank you for formally accepting my solution
Greg
PS The objective function is the function that is minimized to obtain the weight solution. Is that what you really want?
  4 个评论
显示 2更早的评论
prem kumar
prem kumar 2015-3-27
编辑：prem kumar 2015-3-27
i used only one hidden layer with 6 number of hidden neurons. obtained weight and biases values. i am confused which weight i have to used. because it contain layer 1 and layer 2. the layer 1 have five number of column with six number of row which contain numerical values like 0.144.-0.00333....... i think that this values are belongs to input.
same as layer 2 have only 2 column with six row. i think this value is based on output. is it correct?
then the biases value is there 6 values and other 2 values in layer 1 and layer 2.
i can't understand those weight and biases for which i have to use?
this values are enough to form an objective function for my problem? plz help me how to form an objective function?
prem kumar
prem kumar 2015-3-27
sir i had developed neural network in neural network application tool box. how can i do further process. am little confused with code. plz help me to develop the code for my project. if u can i will send my experimental values and output of those experiments. i have to complete on or before 12 april15.
if it possible to do hybrid with this neural network with GA algorithm for optimization. i took this one as a project for its possible to get solution i have little bit knowledge from journals of researchers. they hidden this idea. how can i further develop my project?

请先登录，再进行评论。

更多回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Sequence and Numeric Feature Data Workflows 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by