Skip to main content
U.S. Department of Energy
Office of Scientific and Technical Information

A linear-programming method inspired by the neural networks framework

Conference ·
OSTI ID:5114036

We propose a discrete numerical algorithm for linear programming that has common features with nonlinear optimization algorithms and with neural network models. The ''computation energy'' of our algorithm is not quadratic, but linear, which greatly simplifies the model. The collective computational properties are obtained by dividing the neurons in two classes: primal and dual. The algorithm is parallelisable, easier to code than most classical linear-programming algorithms, and implementable in YLSI. The relationship with other neural network models is discussed.

Research Organization:
Oak Ridge National Lab., TN (USA); Oak Ridge National Lab., TN (USA)
DOE Contract Number:
AC05-84OR21400
OSTI ID:
5114036
Report Number(s):
CONF-880745-2; CONF-880745-; ON: DE88008688
Country of Publication:
United States
Language:
English

Similar Records

Neural network models for Linear Programming
Conference · Sat Dec 31 23:00:00 EST 1988 · OSTI ID:5347615

A neural network for bounded linear programming
Conference · Sat Dec 31 23:00:00 EST 1988 · OSTI ID:5345921

Neural network models for optical computing; Proceedings of the Meeting, Los Angeles, CA, Jan. 13, 14, 1988
Conference · Thu Dec 31 23:00:00 EST 1987 · OSTI ID:6385289