choose learning rate in a neural network

Question

I had built a neural network. In the weights update step the mean error quadratiqur goes directly to 0 for example

mean error quadratic 1 =  1.2
mean error quadratic 1 = 0 
mean error quadratic 1 = 0 
mean error quadratic 1 = 0 
mean error quadratic 1 = 0 
mean error quadratic 1 = 0 ....................

I don't know what is the problem

the size of my neual network is:

input = 324 * 540 target = 10 * 540

when i try with an other data with this size

input = 81* 540 target = 10 * 540

it works.

maybe the problem is in the learning rate ?

please include your code and data, otherwise the only thing we can say is "probably you have an error" — lejlot, Jun 26 '16 at 14:53
my code for calculate the error quadratic is: mse (n) = mse (n) + sumsqrr( error) the parameters are : constant rate = 0.0001 the momentum = 0.3 — Amal Kostali Targhi, Jun 26 '16 at 15:49

user31415 · Answer 1 · 2016-06-25T00:42:10.753

0

This sounds like a problem with the mean error quadratic calculator.

The nn couldn't converge that fast (as you know), and a problem with the nn would probably throw an error. On exception would be if the nn happens to round to numbers that give outputs that match your specific sample (if answer is 0 and all weights round to 0).

Basically, I suspect that this is due to a small set of sample data, or a problem with the mean error quadratic calculator.

Hope this helps!

edited Jun 25 '16 at 00:42

answered Jun 25 '16 at 00:33

user31415

446
7
16

sorry but i didn't understand what you mean – Amal Kostali Targhi Jun 25 '16 at 00:38

choose learning rate in a neural network

1 Answers1