Multi-valued neurons are the neural processing elements with complex-valued weights, huge functionality (it is possible to implement on the single neuron arbitrary mapping describ...
Igor N. Aizenberg, Naum N. Aizenberg, Constantine ...
We study the stability of the Max-Weight protocol for combined routing and scheduling in communication networks. Previous work has shown that this protocol is stable for adversari...
Matthew Andrews, Kyomin Jung, Alexander L. Stolyar
Given an arbitrary network of interconnected nodes, we develop and analyze a distributed strategy that enables a subset of the nodes to calculate any given function of the node val...
Different features have different relevance to a particular learning problem. Some features are less relevant; while some very important. Instead of selecting the most relevant fe...
This paper proposes an initialization of back propagation (BP) networks for pattern classification problems; the weights of hidden units are initialized so that hyperplanes should...