How to Decide size of Neural Network like number of neurons in a hidden layer & Number of hidden layers?

31 views (last 30 days)
sunny B
sunny B on 18 Apr 2013
Commented: Jeong_evolution on 20 Dec 2016
Hi friends, I want to design a neural network which should give one output with five inputs and i have input samples are 432. So please suggest how to design neural network and which type of neural network i should and how to decide number of hidden layers and no of neurons in each hidden layer.

Accepted Answer

Greg Heath
Greg Heath on 19 Apr 2013
Use 1 hidden layer.
Use fitnet for curve-fitting or regression.
Use patternnet for pattern-recognition or classification. For c categories with indices 1:c, the target matrix should contain columns of eye(c). The relationship between target columns and class indices is target = ind2vec(classindices) and classindices = vec2ind(target). Since since the sum of the target columns is 1, one of the rows (usually the last) can be omitted. This reduction is used mostly when c=2.
Find a good value for the number of hidden nodes, H, by trial and error. Create numH*Ntrials nets in a double loop: An outer loop H = Hmin:dH:Hmax over number of hidden nodes and an inner loop i = 1: Ntrials over number of random trn/val/tst data divisions and random weight initialization trials for each value of H.
I typically use numH ~ 10, Ntrials ~ 10 and tabulate results in Ntrials X numH matrices.
Many examples can be obtained by searching the NEWSGROUP and ANSWERS using the keywords
Greg Ntrials Nw
Hope this helps.
Thank you for formally accepting my answer

More Answers (2)

Nduwamungu Corneille
Nduwamungu Corneille on 3 Jun 2013
You may get more details on how many hidden layers and nodes in the following article:
Hope this helps.

abhishek aggarwal
abhishek aggarwal on 1 Apr 2014
Go to the given link. It may help you.

Community Treasure Hunt

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

Start Hunting!