Code generation by a generalized neural network; General principles and elementary examples
Journal Article
·
· Journal of Parallel and Distributed Computing; (USA)
- Caltech Concurrent Computation Project, Caltech 158-79, Pasadena, CA (US)
The authors discuss the possibility of using neural network optimization to perform optimized code generation, and list possible benefits. The approach used by Hopfield and Tank to treat the traveling salesman is extended to cover the motion of abstract quantities through a computer. A simple general method for constructing complicated syntactic constraints is introduced, applicable to both sequential and parallel target architectures. They test the approach on some very elementary examples of sequential code, by simulation.
- OSTI ID:
- 5345748
- Journal Information:
- Journal of Parallel and Distributed Computing; (USA), Journal Name: Journal of Parallel and Distributed Computing; (USA) Vol. 6:2; ISSN JPDCE; ISSN 0743-7315
- Country of Publication:
- United States
- Language:
- English
Similar Records
A neural network algorithm for the multiple traveling salesmen problem
A concurrent neural network algorithm for the traveling salesman problem
Computational-complexity reduction for neural network algorithms
Technical Report
·
Mon Oct 31 23:00:00 EST 1988
·
OSTI ID:6600625
A concurrent neural network algorithm for the traveling salesman problem
Conference
·
Thu Dec 31 23:00:00 EST 1987
·
OSTI ID:5271931
Computational-complexity reduction for neural network algorithms
Journal Article
·
Tue Feb 28 23:00:00 EST 1989
· IEEE (Institute of Electrical and Electronics Engineers) Transactions on Systems, Man, and Cybernetics; (USA)
·
OSTI ID:5242987