Linked assembly of neural networks to solve the interconnection problem

In order to reduce the complexity of training a neural network, partitioning of the problem is introduced to facilitate the identification of smaller and, if possible, replicable networks which are more readily trained. An interactive software system for the linked assembly of these neural networks (ASLANN) has been developed and is used to generate the final network. To demonstrate this technique, the application of back propagation neural networks to the routing of an integrated circuit is discussed.<
>