TY - JOUR
T1 - A one-layer recurrent neural network with a discontinuous activation function for linear programming
AU - Liu, Qingshan
AU - Wang, Jun
PY - 2008/5
Y1 - 2008/5
N2 - A one-layer recurrent neural network with a discontinuous activation function is proposed for linear programming. The number of neurons in the neural network is equal to that of decision variables in the linear programming problem. It is proven that the neural network with a sufficiently high gain is globally convergent to the optimal solution. Its application to linear assignment is discussed to demonstrate the utility of the neural network. Several simulation examples are given to show the effectiveness and characteristics of the neural network. © 2007 Massachusetts Institute of Technology.
AB - A one-layer recurrent neural network with a discontinuous activation function is proposed for linear programming. The number of neurons in the neural network is equal to that of decision variables in the linear programming problem. It is proven that the neural network with a sufficiently high gain is globally convergent to the optimal solution. Its application to linear assignment is discussed to demonstrate the utility of the neural network. Several simulation examples are given to show the effectiveness and characteristics of the neural network. © 2007 Massachusetts Institute of Technology.
UR - http://www.scopus.com/inward/record.url?scp=43449132396&partnerID=8YFLogxK
UR - https://www.scopus.com/record/pubmetrics.uri?eid=2-s2.0-43449132396&origin=recordpage
U2 - 10.1162/neco.2007.03-07-488
DO - 10.1162/neco.2007.03-07-488
M3 - RGC 21 - Publication in refereed journal
SN - 0899-7667
VL - 20
SP - 1366
EP - 1383
JO - Neural Computation
JF - Neural Computation
IS - 5
ER -