tags:

views:

93

answers:

0
+1  Q: 

How does the cross-entropy error function work in an ordinary back-propagation algorithm?

I'm working on a feed-forward backpropagation network in C++ but cannot seem to make it work properly. The network I'm basing mine on is using the cross-entropy error function. However, I'm not very familiar with it and even though I'm trying to look it up I'm still not sure. Sometimes it seems easy, sometimes difficult. The network will solve a multinomial classification problem and as far as I understand, the cross-entropy error function is suitable for these cases. Someone that knows how it works?

related questions

Advice for a C, CUDA, & ANN Newbie?
Are evolutionary algorithms and neural networks used in the same problem domains?
Looking for interesting topic from neural networks area.
Looking for a Good Reference on Neural Networks
Can a perceptron be used to detect hand-written digits?
Best approach to what I think is a machine learning problem
Activation function when training a single layer perceptron
Any good SharpNEAT tutorial?
What are some good resources for learning about Neural Networks?
Neural Network Structure
How to find the value of a neuron in a neural network
Math optimization in C#
Prerequisites Needed to Read Books on Neural Networks (and understand them)
Artificial Neural Network Question
What are areas where you can program artificial intelligence?
What is the coolest AI project you've heard of?
Non-mathematical Description of Neural Networks
What is the relationship between bayesian and neural networks?
Find class probabilities in matlab PNN and make ROC plot
What are some practical applications for a single layer perceptron?
What are some good resources for programming Artificial Intelligence?
Neural Networks or Human-computer interaction
Neural Network example in .NET
C++/Java Performance for Neural Networks?
What lightweight neural networks are there for Java?