NeuralNET with Categorical Variables.
2 views (last 30 days)
Show older comments
I am trying to train a NN with a set number of Input variables, say "n", and a set of outputs say "m". I have two categories 1 and 2 . I have the data available for category 1 and category 2 both 1000 in number. both have the same number of Inputs/variables and same number of output/variables. Ofcourse depending on which category it belongs to, the outputs vary. I want to train them together that is I have 2 categories (1, and 2) and "n" input variables, generating "m" outputs. How do I set up the network (feed forward net is what I am using). I have done separately two networks for each and they work fine. but I want t train them together. Please help. Thanks in advance.
This is what I am currently using for single NN:
net = feedforwardnet(hiddenLayerSize);
net = configure(net, x, t);
[net,tr] = train(net,x,t);
Where hiddenLayerSize is number of nodes in hidden layer. Currently I have about 13 inputs 10 Hidden nodes and 9 outputs for each network.
0 Comments
Answers (0)
See Also
Categories
Find more on Sequence and Numeric Feature Data Workflows in Help Center and File Exchange
Products
Community Treasure Hunt
Find the treasures in MATLAB Central and discover how the community can help you!
Start Hunting!