I need my network to produce output like 234,231.......(values in range 200-300).
So I have created a 5-4-1 FF network with Sigmoid activation function in Hidden Layer and linear activation at output layer. Are these correct network activation functions for my network?
And since i am using Sigmoid function at hidden layer the output of hidden layer will be [0-1].
And calculation at hidden layer are summation of all Wts*inpus and then sigmoid function y=1/(1+e^-x). Is this correct what I am thinking?
Neural network training can be made more efficient if you perform certain preprocessing steps on the network inputs and targets. It is standard practice to normalize the inputs before applying them to the network. Generally, the normalization step is applied to both the input vectors and the target vectors in the data set. In this way, the network output always falls into a normalized range. The network output can then be reverse transformed back into the units of the original target data when the network is put to use in the field. So don't care about the dynamic range of neither the input nor the output data set. If you use Matlab, you can try "mapminmax" built-in function to do this task.
Concerning the type of the transfer functions of the hidden and output layer, this combination is the most famous one although it depends on the nature of the data. I thas been proven that this topology with sufficent hidden neurons achieves the universal approximation property.
Is it always necessary to normalise data or it improves performance?
it improves the performance. I recommend reading this page http://www.mathworks.es/es/help/nnet/ug/collect-and-prepare-the-data.html
Good luck.
All the input vectors and the target vectors have to be scaled bewteen 0 and 1 or -1 and 1. This scaling has to be done by column (different variables may have non comparable values). To do that you have to establish the max and the min value of each variable (Max and Min). Then you have to decide the range of the new scaled values (High and Low). Now you have to calculate two new coefficient Scale and Offset in this way: Scale=(High-Low)/(Max-Min); Offset=(Max*Low-Min*High)/(Max-Min).
At this point you have to rewrite each value of considered variable in this way:
NewVar=Var*Scale+Offset.
You need to create a set of vectors for each of the dataset variables:
Max=new float[NumVariables]; Min=new float[NumVariables]; Scale=new float[NumVariables]; Offset=new float [NumVariables]. That because you have to scale each variable in an independent way. High and Low, instead has to be the same for the whole dataset. For the input vectors, I suggest [0,1] if the values of the dataset represent real quantity (that is : the lowest values represent small quantities) and [-1,+1] if the values represent qualitative features.
After the training of ANN you can recode the output into the original range of value using the same equation: Var=(NewVar-Offset)/Scale.
Good work
Massimo Buscema
- Badges
- Science topic