Multiple-inputn Recurrent- Elman Neural Network

2 views (last 30 days)
Hello ; Is it possible to use Recurrent neural network, Elman neural network in matlab "elmannet", with Multiple-input for multi-class classification. in the documentations, they present juste an exemple with one input wich represents one class.
[X,T] = simpleseries_dataset;
net = elmannet(1:2,10);
[Xs,Xi,Ai,Ts] = preparets(net,X,T);
net = train(net,Xs,Ts,Xi,Ai);
view(net)
Y = net(Xs,Xi,Ai);
perf = perform(net,Ts,Y)

Answers (1)

Greg Heath
Greg Heath on 28 Feb 2017
It doesn't make any sense to use a timeseries net for classification.
Use patternnet:
help patternnet
doc patternnet
Search Newsgroup and ANSWERS using
greg patternnet
Hope this helps.
Greg
  1 Comment
arnaud ensberg
arnaud ensberg on 1 Mar 2017
i used patternnet to classification, but i want use Recurrent neural network To predict the rest of the sequence among multi sequences .

Sign in to comment.

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!