Optimization with Neural Networks
(1999) In Lecture Notes in Physics 522. p.243-256- Abstract (Swedish)
- The recurrent neural network approach to combinatorial optimization has during the last decade evolved into a competitive and versatile heuristic method, that can be used on a wide range of problem types. In the state-of-the-art neural approach the discrete elementary decisions (not necessarily binary) are represented by continuous Potts mean-field neurons, interpolating between the available discrete states, with a dynamics based on iteration of a set of mean-field equations. Driven by annealing in an artificial temperature, they will converge into a candidate solution.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/986dcb1b-ffb2-4275-b4e6-de82172f542d
- author
- Söderberg, Bo LU
- organization
- publishing date
- 1999
- type
- Chapter in Book/Report/Conference proceeding
- publication status
- published
- subject
- host publication
- Scientific Applications of Neural Nets
- series title
- Lecture Notes in Physics
- editor
- Clark, J. W. ; Lindenau, T. and Ristig, M. L.
- volume
- 522
- pages
- 14 pages
- publisher
- Springer
- language
- English
- LU publication?
- yes
- id
- 986dcb1b-ffb2-4275-b4e6-de82172f542d
- alternative location
- https://www.springer.com/la/book/9783662142356
- date added to LUP
- 2019-05-13 20:34:17
- date last changed
- 2020-01-14 14:10:13
@inbook{986dcb1b-ffb2-4275-b4e6-de82172f542d, abstract = {{The recurrent neural network approach to combinatorial optimization has during the last decade evolved into a competitive and versatile heuristic method, that can be used on a wide range of problem types. In the state-of-the-art neural approach the discrete elementary decisions (not necessarily binary) are represented by continuous Potts mean-field neurons, interpolating between the available discrete states, with a dynamics based on iteration of a set of mean-field equations. Driven by annealing in an artificial temperature, they will converge into a candidate solution.}}, author = {{Söderberg, Bo}}, booktitle = {{Scientific Applications of Neural Nets}}, editor = {{Clark, J. W. and Lindenau, T. and Ristig, M. L.}}, language = {{eng}}, pages = {{243--256}}, publisher = {{Springer}}, series = {{Lecture Notes in Physics}}, title = {{Optimization with Neural Networks}}, url = {{https://www.springer.com/la/book/9783662142356}}, volume = {{522}}, year = {{1999}}, }