Neural network processing for multiset data

This paper introduces the notion of the variadic neural network (VNN). The inputs to a variadic network are an arbitrary-length list of n-tuples of real numbers, where n is fixed. In contrast to a recurrent network which processes a list sequentially, typically being affected more by more recent list elements, a variadic network processes the list simultaneously and is affected equally by all list elements. Formally speaking, the network can be seen as instantiating a function on a multiset along with a member of that multiset. I describe a simple implementation of a variadic network architecture, the multi-layer variadic perceptron (MLVP), and present experimental results showing that such a network can learn various variadic functions by back-propagation.