Counterpropagation Network
The counterpropagation network is a hybrid network. It consists of an outstar network and a competitive filter network. It was developed in 1986 by Robert Hecht-Nielsen. It is guaranteed to find the correct weights, unlike regular back propagation networks that can become trapped in local minimums during training.
The input layer neurodes connect to each neurode in the hidden layer. The hidden layer is a Kohonen network which categorizes the pattern that was input. The output layer is an outstar array which reproduces the correct output pattern for the category.
Training is done in two stages. The hidden layer is first taught to categorize the patterns and the weights are then fixed for that layer. Then the output layer is trained. Each pattern that will be input needs a unique node in the hidden layer, which is often too large to work on real world problems.
2 responses so far ↓
1 glanny // Feb 29, 2008 at 12:07 pm
Thank you for this information, but how to combine the hidden layer (competitive layer) with the output layer (outstar structure by Grossberg)?
and for the training process (two stages?).
2 herself // Mar 1, 2008 at 12:12 am
* 3/10 Sorry— still digging out my desk here. I don’t know the answer on the top of my head. I’m going to have to hunt down the source I used and see if I can diagram out what he was doing. I’ll post the information here as soon as I have it.
Let me take a look and see if I can’t come up with a more detailed description.
I am out of town this week, so check back late next week, or I’ll drop you an email.
You must log in to post a comment.