Highlighted are operational issues of software-based Hopfield neural network DCA schemes under real-time constraints. In particular, parameter tuning necessitated by rapid convergence of iterative solutions is considered with performance evaluation based on a simulation model.
Inspec keywords: statistical analysis; tuning; telecommunication computing; iterative methods; convergence of numerical methods; Hopfield neural nets; channel allocation
Other keywords:
Subjects: Other topics in statistics; Neural computing techniques; Communications computing; Interpolation and function approximation (numerical analysis); Communication system theory; Other topics in statistics; Interpolation and function approximation (numerical analysis)
References
-
-
1)
- S. Abe . Global convergence and suppression of spurious states of Hopfield neural networks. IEEE Trans. Circuits Syst. , 4 , 246 - 257
-
2)
- E. Del Re , R. Fantacci , L. Ronga . A dynamic channel allocation technique based on Hopfield neural networks. IEEE Trans. Veh. Technol. , 1 , 26 - 32
-
3)
- O. Lazaro , D. Girma . A Hopfield neural-network-based dynamic channel allocation with handoff channel reservation control. IEEE Trans. Veh. Technol. , 5 , 1578 - 1587
-
4)
- Lazaro, O., Girma, D.: `Quality of service and grade of service optimisation with distributed dynamic channel allocation schemes based on Hopfield neural network algorithms', IEEE VTC 2000 Fall, September 2000, Boston, MA, USA.
-
5)
- O. Lazaro , D. Girma . Impact of decentralization on the performance of a Hopfield neural network-based DCA scheme. IEEE Commun. Lett. , 11 , 444 - 446
-
1)
Related content