A Novel Weight Initialization Method for the Random Neural Network

In this paper, the authors propose a novel weight initialization method for the Random Neural Network. The method relies on approximating the signal-flow equations of the network to obtain a linear system of equations with non-negativity constraints. For the solution of the formulated linear Nonnegative Least Squares problem they have developed an improved projected gradient algorithm. It is shown that supervised learning with the developed initialization method has better performance than learning with random initialization for a combinatorial optimization emergency response problem.