Abstract
This paper studies the performance of Hopfield's neural network also known as the McCulloch-Pitts model, in solving optimization problems. We have discovered that it can not solve many problems satisfactorily including the Traveling Salesman Problem (TSP). But, it can solve some problems quite well, e.g., the Graph Coloring Problem (GCP). Near-optimal solutions can be easily obtained using our methodology, and the performances, contrary to common belief, are not so much affected by the parameters of the energy function, if the parameters are within certain range.
Original language | English (US) |
---|---|
Pages (from-to) | 151 |
Number of pages | 1 |
Journal | Neural Networks |
Volume | 1 |
Issue number | 1 SUPPL |
DOIs | |
State | Published - 1988 |
Event | International Neural Network Society 1988 First Annual Meeting - Boston, MA, USA Duration: Sep 6 1988 → Sep 10 1988 |
ASJC Scopus subject areas
- Cognitive Neuroscience
- Artificial Intelligence