A new objective function for neural net classifier design is presented, which has more free parameters than the classical objective function. An iterative minimization technique f...
Jiang Li, Michael T. Manry, Li-min Liu, Changhua Y...
The advent of large scale multi-hop wireless networks highlights problems of fault tolerance and scale in distributed system, motivating designs that autonomously recover from tra...
This paper introduces a learning method for two-layer feedforward neural networks based on sensitivity analysis, which uses a linear training algorithm for each of the two layers....
Abstract--Motivated by applications of distributed linear estimation, distributed control, and distributed optimization, we consider the question of designing linear iterative algo...
Abstract. We propose a unifying framework for polyhedral approximation in convex optimization. It subsumes classical methods, such as cutting plane and simplicial decomposition, bu...