how to apply DATA to inputs in neural network MLP?
1 view (last 30 days)
Show older comments
hello, i want to create a network but i don't know how to apply my data.my data is 64 person that 15 people have park , 20 hunt ,13 als and 16 control. each one has 13 feature and about 300 row (not all of them exactly the same).i want to input my data for training. the output of this data is 4 neuron (als, hunt,park,cont). the network should diagnose this 4. how should i apply this input in MLP? i will be appriciate if any one can help me. ps, i attached each of my data not all of them.
2 Comments
Walter Roberson
on 1 Oct 2016
What do the rows represent? How do you know the boundary between one person and the next in the data?
I gather you are looking at Parkinson's, Huntington's, Amyotrophic Lateral Sclerosis, and controls.
Answers (1)
Greg Heath
on 1 Oct 2016
Data must consist of N pairs:
I-dimensional "I"nputs in an I x N matrix
and a corresponding
O x N "O"utput target matrix with O-dimensional columns
[ I N ] = size(input)
[ O N ] = size(target)
For a simple classification example use the commands
help patternnet
doc patternnet
for more extensive examples search BOTH NEWSGROUP and ANSWERS with
greg patternnet tutorial
and
greg patternnet
Hope this helps,
Thank you for formally accepting my answer
Greg
See Also
Categories
Find more on Sequence and Numeric Feature Data Workflows 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!