CALCULATING WEIGHT MATRIX OF NEURAL NETWORK FOR RESOURCE LEVELING

A new approach for the computation of the weight matrix of a Hopfield neural network for resource leveling is introduced. The proposed method achieves significantly improved efficiency over the conventional technique of employing the functional expressions of the weights by exploiting the structural properties of the matrices arising in the formulation of the resource leveling problem as a quadratic zero-one optimization. These structural properties are identified and stated in terms of template-matrix contributions of the cost and constraint functions of the quadratic optimization, to the weight matrix of the Hopfield neural network. It is shown that by using these templates, the weight matrix can be filled in directly, based on the early start schedule of a project.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/08873801
• Corporate Authors:

  American Society of Civil Engineers

  345 East 47th Street
  New York, NY  United States  10017-2398
• Authors:
  • Savin, D
  • Alkass, S
  • Fazio, P
• Publication Date: 1998-10

Language

• English

Media Info

• Features: Appendices; Figures; References;
• Pagination: p. 241-248
• Serial:
  • Journal of Computing in Civil Engineering
  • Volume: 12
  • Issue Number: 4
  • Publisher: American Society of Civil Engineers
  • ISSN: 0887-3801
  • Serial URL: https://ascelibrary.org/journal/jccee5

Subject/Index Terms

• TRT Terms: Calculation; Constraints; Costs; Lagrangian functions; Mathematical matrices; Neural networks; Optimization; Quadratic equations; Resource allocation
• Uncontrolled Terms: Templates
• Old TRIS Terms: Computations; Weight matrix
• Subject Areas: Administration and Management; Finance; Highways; I10: Economics and Administration;

Filing Info

• Accession Number: 00756602
• Record Type: Publication
• Contract Numbers: GR/J16121
• Files: TRIS
• Created Date: Nov 12 1998 12:00AM