Encog 3.0 backpropagation

Posted by Mohamed Shouman on Stack Overflow See other posts from Stack Overflow or by Mohamed Shouman
Published on 2012-12-01T23:01:22Z Indexed on 2012/12/01 23:03 UTC
Read the original article Hit count: 169

Filed under:
|

I have a question...I am using Encog framework to train a network using BP. I am training the network using images that has some object say a cat, telling the network which images are cats and which are not.

Bellow are my Neural Network results

actual=0.1545868370551181 ideal=0.0,actual=0.797896306829758 ideal=1.0,actual=0.1545868370551181 ideal=0.0,actual=0.797896306829758 ideal=1.0

It is my understanding that since different pictures are presented to network some look like cat for example then they should have higher percentage...but i keep getting same percentage for any pic that has a cat which is 0.79 and for other pics i get 0.15...how can i solve this issue!, what is the intuition behind whats going on!

Many thanks

© Stack Overflow or respective owner

Related posts about java

Related posts about encog