01-15-2017 11:44 PM
Can someone pls let me know how to calculate a prediction (continuous) from a set of input variables (continuous) using the weights and bias at hidden nodes (sigmoid) and the output node (linear)? This is to manually verify the results obtained from neuralnet.
Solved! Go to Solution.
01-16-2017 07:55 AM
Maybe this can help you: https://excel.ucf.edu/classes/2007/Spring/appsII/Chapter1.pdf
01-16-2017 07:24 PM
Thanks a lot.
I have used the NeuralNet output weights to calculate the sigmoid transformation of weighted sum of the inputs. The mistake I have made was calculating the output without realizing that NeuralNet has normalised the attributes to fall within -1 and 1. Now all sorted.