A neural network approach to set up the Benes switch
Nagib Hakim, H. E. Meadows · 2002
A novel technique for setting up the Benes switch that has essentially optimal time complexity when implemented on a neural network is presented. This approach consists of defining distances between input or output ports and expressing the Banyan network's ability to realize a given permutation in terms of a distance matrix. This description allows a neural network implementation of the setup algorithm. It is shown that the neural network converges to a solution that will allow the switch to self-route the information according to the desired permutation. The time complexity of this operation is closer to optimal and the hardware simpler to implement than with previously presented algorithms.>