Estimation of attraction domain and exponential convergence rate of dynamic feedback neural nets
2000
This paper obtains some new estimation results about the attraction domain of memory patterns and exponential convergence rate of the network trajectories to memory patterns for continuous associative memory dynamic feedback neural networks. Exponential convergence rate went up faster in our results than those results in the literature. These results can be used for evaluation of fault-tolerance capability and the synthesis procedures for continuous associative memory dynamic feedback neural networks. We give one design example to demonstrate the effectiveness of our theorems.
Keywords:
- Rate of convergence
- Convergence (routing)
- Network synthesis filters
- Artificial neural network
- Exponential function
- Machine learning
- Pattern recognition
- Exponential stability
- Content-addressable memory
- Artificial intelligence
- Attraction
- Control theory
- Computer science
- Algorithm
- Neurofeedback
- Theoretical computer science
- Content-addressable storage
- Fault tolerance
- Correction
- Source
- Cite
- Save
- Machine Reading By IdeaReader
8
References
2
Citations
NaN
KQI