Use of neural nets in channel routing
- 1 January 1989
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
Abstract
The channel routing problem is solved using a massively parallel processor based on the artificial neural system (ANS) computational model. In this model the functional behavior of the human designer is emulated by expressing problem constraints as interconnection weights between neural cells (computational elements), using very simple computational elements for neural cells and massive parallelism to solve problems. The algorithm constraints are expressed as interconnection weights. By making the artificial neural cells work collectively on a task, a solution is obtained after each of the neural cells settles to a stable state.Keywords
This publication has 11 references indexed in Scilit:
- Recent Advances in Near-Field-Based Small Form Factor Optical StorageIEEE Transactions on Magnetics, 2007
- Net characterization based channel router: FT routerPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Neural networks as a new strategy for computingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Parallel channel routingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- A parallel simulated annealing algorithm for channel routing on a hypercube multiprocessorPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- An introduction to neural computingNeural Networks, 1988
- An introduction to computing with neural netsIEEE ASSP Magazine, 1987
- Neural networks and physical systems with emergent collective computational abilities.Proceedings of the National Academy of Sciences, 1982
- Efficient Algorithms for Channel RoutingIEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 1982
- A “Dogleg” channel routerPublished by Association for Computing Machinery (ACM) ,1976