How to train a Matlab Neural Network using matrices as inputs?
5 views (last 30 days)
Show older comments
Vimukthi Weerasiri
on 5 Jan 2016
Answered: Greg Heath
on 6 Jan 2016
I am making 8 x 8 tiles of Images and I want to train a RBF Neural Network in Matlab using those tiles as inputs. I understand that I can convert the matrix into a vector and use it. But is there a way to train them as matrices? (to preserve the locality) Or is there any other technique to solve this problem?
1 Comment
Sivakumaran Chandrasekaran
on 5 Jan 2016
in MATLAB, if you write y=1.. is also a MATRIX.. you can also train them as matrices
Accepted Answer
Greg Heath
on 6 Jan 2016
Standard procedure:
Each input and output must be a column vector. If your original input is an image, just use the column operator x = image(:). However, if you wish to consider several images, each image will be a column in the network's input matrix.
No biggie
Hope this helps.
Thank you for formally accepting my answer
Greg
0 Comments
More Answers (0)
See Also
Categories
Find more on Image 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!