Abstract
A variant of the Hopfield network, called the modified Hopfield network is formulated. This network which consists of two mutually recurrent networks has more free parameters than the well-known Hopfield network. Stability analysis of this network is presented. The analysis is carried out in the time domain with an application of the Lyapunov method and robust control Lyapunov function. The current flow in the network is treated as a "control". This "controller" is shown to guarantee "a practically stabilizing control". Analysis of the Hopfield network is also included for completion.
Recommended Citation
J. Shen and S. N. Balakrishnan, "Robustness Analysis of Hopfield and Modified Hopfield Neural Networks in Time Domain," Proceedings of the 37th IEEE Conference on Decision and Control, 1998, Institute of Electrical and Electronics Engineers (IEEE), Jan 1998.
The definitive version is available at https://doi.org/10.1109/CDC.1998.760835
Meeting Name
37th IEEE Conference on Decision and Control, 1998
Department(s)
Mechanical and Aerospace Engineering
Keywords and Phrases
Hopfield Neural Nets; Lyapunov Method; Lyapunov Methods; Modified Hopfield Neural Networks; Mutually Recurrent Networks; Neurocontrollers; Practically Stabilizing Control; Robust Control; Robust Control Lyapunov Function; Robustness Analysis; Time Domain; Time-Domain Analysis
Document Type
Article - Conference proceedings
Document Version
Final Version
File Type
text
Language(s)
English
Rights
© 1998 Institute of Electrical and Electronics Engineers (IEEE), All rights reserved.
Publication Date
01 Jan 1998
