Hopfield and Tank have shown that neural networks can be used to solve certain computationally hard problems, in particular they studied the Traveling Salesman Problem (TSP). Based on network simulation results they conclude that analog VLSI neural nets can be promising in solving these problems. Recently, Wilson and Pawley presented the results of their simulations which contradict the original results and cast doubts on the usefulness of neural nets. In this paper we give the results of our simulations that clarify some of the discrepancies. We also investigate the scaling of TSP solutions found by neural nets as the size of the problem increases. Further, we consider the neural net solution of the Clustering Problem, also a computationally hard problem, and discuss the types of problems that appear to be well suited for a neural net approach.
This is a preview of subscription content, log in to check access.
Buy single article
Instant access to the full article PDF.
Price includes VAT for USA
Subscribe to journal
Immediate online access to all issues from 2019. Subscription will auto renew annually.
This is the net price. Taxes to be calculated in checkout.
Baum EB (1986) Towards practical neural computation for combinatorial optimization problems. In: Denker JS (ed) Neural networks for computing. American Institute of Physics, New York, NY, pp 53–58
Cohen MA, Grossberg S (1983) Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans Syst Man Cybern 13:813–825
Feller W (1959) An introduction to probability theory and its applications, 2nd edn, vol 1. Wiley, New York, p 58
Fogelman Soulie F, Weisbuch G (1987) Random iterations of threshold networks and associative memory. SIAM J Comput 16:203–220
Forgy EW (1965) Cluster analysis of multivariate data: efficiency versus interpretability of classifications. Biometr Soc Meetings Riverside, California. Biometrics (abstr) 21:768
Gear CW (1971) Numerical initial value problems in ordinary differential equations. Prentice-Hall, Englewood Cliffs
Hopfield JJ (1984) Neurons with graded response have collective computational properties like those of two-state neurons. Proc Natl Acad Sci USA 81:3088–3092
Hopfield JJ, Tank DW (1985) Neural computation of decisions in optimization problems. Biol Cybern 52:141–152
Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice-Hall, Englewood Cliffs
Kamgar-Parsi B, Gualtieri JA, Devaney JE, Kamgar-Parsi B (1988) Clustering with neural networks. In: Proceedings of the 2nd Symposium on Massively Parallel Scientific Computation. IEEE Computer Society Press, Washington, DC, pp 31–38
Kamgar-Parsi B, Kamgar-Parsi B (1987) An efficient model of neural networks for optimization. In Proceedings of the IEEE First International Conference on Neural Networks, vol 3. SOS Printing, San Diego, CA, pp 785–790
Kamgar-Parsi B, Kamgar-Parsi B (1990) Importance of being synchronous in neural networks. University of Maryland, Center for Automation Research Technical Report
Mead C (1989) Analog VLSI and neural systems. Addison-Wesley, Reading Mass
Mjolsness E (1987) Control of attention in neural networks. In: Proceedings of the IEEE First International Conference on Neural Networks, vol 2. SOS Printing, San Diego, CA, pp 567–574
Wilson GV, Pawley GS (1988) On the stability of the Travelling Salesman Problem algorithm of Hopfield and Tank. Biol Cybern 57:63–70
Zak M (1988) Terminal attractors for addressable memory in neural networks. Phys Lett A 133:18–22
About this article
Cite this article
Kamgar-Parsi, B., Kamgar-Parsi, B. On problem solving with Hopfield neural networks. Biol. Cybern. 62, 415–423 (1990). https://doi.org/10.1007/BF00197648
- Neural Network
- Travel Salesman Problem
- Travel Salesman Problem
- Network Simulation
- Hard Problem