K. Koutroumbas et N. Kalouptsidis, NEURAL-NETWORK ARCHITECTURES FOR SELECTING THE MAXIMUM INPUT, International journal of computer mathematics, 67(1-2), 1998, pp. 25-32
In this paper two neural network architectures for selecting the maxim
um among a set of numbers are introduced. The first architecture is re
current and relies on the Hamming MaxNet. The second architecture is f
eedforward, featuring modularity and pipelineability.