convergence of neural network back propagation

Asked Jun 26 '16 at 00:10

Active Dec 06 '19 at 17:21

Viewed 37 times

I had built a neural network in the weights update step the mean error square go directly to 0 for example

mean error square 1 =  1.2
mean error square 2 = 0 
mean error square 3 = 0 
mean error square 4 = 0 
mean error square 5 = 0 
mean error square 6 = 0 ....................

I don't know what is the problem the size of my neural 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 in the learning rate?

edited Dec 06 '19 at 17:21

Cœur

37,241
25
195
267

asked Jun 26 '16 at 00:10

Amal Kostali Targhi

If you want help, you need to at least provide a [mcve](http://stackoverflow.com/help/mcve). – jorgenkg Jun 26 '16 at 07:06
I dont understand your question. Could you please provide a more clear description. – Bastian Jun 26 '16 at 08:59

convergence of neural network back propagation

0 Answers0