2D array as input to neural network

2 views (last 30 days)
My neural network has 2 feature variables each with a length of 112. Further I have 5 samples from each person and there are total 5 persons.
input= 2 rows, 112(per class feature vector length), 5 persons and 5 samples per person, so its (2, 112 x 5 x 5)
output = (5 (classes), 112 x 5 x 5)
I intend to specify the basic unit of classification as 2 x 112. Any idea how can I do this ? Currently its consider each column 2 x 1 as one input.
  2 Comments
Walter Roberson
Walter Roberson on 19 Feb 2013
Did you experiment with transposing the input array to 112 x 2, just to see what would happen?
sajid
sajid on 19 Feb 2013
I guess in that case it will be 112 x 1 as each column will be treated as a feature vector of length 112. Kindly correct me if I am wrong.

Sign in to comment.

Accepted Answer

Greg Heath
Greg Heath on 19 Feb 2013
Edited: Greg Heath on 19 Feb 2013
Burp...(coke, not coffee).
The input matrix must contain N I-dimensional column vectors
[ I N ] = size(input) % [ 224 25 }
The target matrix contains N O-dimensional column vectors
[ O N ] = size(output)% [ 5 25 ]
For c class classification, the N target vectors are columns of the c-dimensional unit matrix eyec = eye(c) with the row index of the "1" equal to the class index of the corresponding input column.
The target matrix can be formed from a class index row vector (and vice versa via the functions ind2vec and vec2ind. The column sum is an N-dimensional row vector of ones (ones(1,N)) and the row sum is the c-dimensional column vector (c*ones(c,1)).
I believe the training function of the obsolete newpr and current patternnet is 'trainscg' which uses batch training. The order of the vectors is arbitrary.
Hope this helps.
Thank you for formally accepting my answer
Greg
P.S. You should investigate reducing the dimensionaliy of the 224 dimensional input vectors.

More Answers (1)

Walter Roberson
Walter Roberson on 19 Feb 2013
A feature cannot be a 2D array. You can reshape() to make each feature a column.
  5 Comments
Walter Roberson
Walter Roberson on 19 Feb 2013
I do not know if it is possible to treat different elements differently. Maybe with custom functions of some kind. Greg would know; he might visit the topic in anywhere between 4 hours and 4 days (depending on when he gets enough coffee in his system.)
Greg Heath
Greg Heath on 19 Feb 2013
It doesn't matter how your input rows are ordered.
However, I suggest transforming to cartesian coordinates so that
input = [ x ; y ]
with
size(y) = size(x) = [ 112 25 ]

Sign in to comment.

Community Treasure Hunt

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

Start Hunting!