Optimization with Neural Networks

Summary, in 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.

• Author: Bo Söderberg
• Editor: J. W. Clark; T. Lindenau; M. L. Ristig
• Department/s: Computational Biology and Biological Physics - Has been reorganised
• Publishing year: 1999
• Language: English
• Pages: 243-256
• Publication/Series: Lecture Notes in Physics
• Volume: 522
• Links: https://www.springer.com/la/book/9783662142356
• Document type: Book chapter
• Publisher: Springer
• Topic: Computational Mathematics
• Status: Published