Question

["Reza" <davood@ix.netcom.com>]

Hello,

I'm trying to make a network for word recognition with multilayer output, the first layer (or sublayer of the output) consists of 108 units and the second one has 100 units and there is a bidirectional connection between these 2 sublayers. The problem is I don't know how to represent it in the network to have these 2 sublayers in the Environment in order to be able to define the distribution of activation for each stimulus. Any advice/help will be greatly appreciated.

Reza