How to implement neural network in matlab using newff command

18 views (last 30 days)
Hi, I want to implement backpropagation neural network using newff command. I have input p=[1 2;1 2] target t=[0 2] I m using newff command but it is not working properly. how can i come to know about the output and the error of network? There is another prob also. I have used nntool but it is giving wrong output. Can we have any video which can illustrate the use of nntool.

Accepted Answer

Greg Heath
Greg Heath on 6 Dec 2013
>> help newff
newff Create a feed-forward backpropagation network.
Obsoleted in R2010b NNET 7.0. Last used in R2010a NNET 6.0.4.
The recommended function is feedforwardnet.
I disagree with the feedforwardnet recommendation:
help fitnet % for regression and curve-fitting documentation and example
doc fitnet % additional info
help patternnet % for classification and pattern-recognition documentation and example
doc patternnet % additional info
Both fitnet and patternnet call feedforwardnet. Feedforwardnet NEVER has to be called directly.
Use the help and doc commands for info on any function or command
Always use one of the MATLAB neural net data sets when asking a question in the NEWSGROUP or ANSWERS
help nndatasets
doc nndatasets
HTH
Thank you for formally accepting my answer
Greg

More Answers (0)

Categories

Find more on Deep Learning Toolbox in Help Center and File Exchange

Tags

Community Treasure Hunt

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

Start Hunting!