Creating a feature vector & target vector to feed into neural network

2 views (last 30 days)
Hi,
I am working on handwritten character recognition using neural networks. I am extracting 85*1 features of single image (ex : character 'A'). In the same way I am getting 85 *1 features for each 26 characters. Now, I want to create feature vector and target vector(26 classes) for these extracted features. Can anyone please tell me how to create a single feature vector and target vector for all those extracted features of 26 characters so that I can feed them to neural network?

Accepted Answer

Greg Heath
Greg Heath on 11 Apr 2014
size(input) = [ 85 26 ]
target = ind2vec(1:26);
net = patternnet(H) ;% Determine H by trial and error
help patternnet
doc patternnet
Also search using
greg patternnet Ntrials
Hope this helps.
Thank you for formally accepting my answer
Greg

More Answers (0)

Categories

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

Community Treasure Hunt

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

Start Hunting!