Sparse matrix as features in neural network

Hi to all! When I train my neural network, my input data set is very large and I cannot handle it with Matlab. The matrix is sparse. How can I handle this as an input to a net? I think the train() function in neural network requires in full matrix inputs (so I'm afraid I can't use the sparse representation done with the function sparse()). Does anyone have experience to do this? Thanks!

[Greg Heath]

Check with MATLAB directly.

Answer 1

[Greg Heath]

I think it is as simple as reading the documentation

 help sparse
 doc sparse

Hope this helps.

Thank you for formally accepting my answer

Greg