Multilayer feedforward networks are universal approximators
Neural Networks
State space neural network. Properties and application
Neural Networks
Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory
Static and Dynamic Neural Networks: From Fundamentals to Advanced Theory
Neural Networks: A Comprehensive Foundation (3rd Edition)
Neural Networks: A Comprehensive Foundation (3rd Edition)
On-line learning algorithms for locally recurrent neural networks
IEEE Transactions on Neural Networks
Locally recurrent globally feedforward networks: a critical review of architectures
IEEE Transactions on Neural Networks
Model-Based Fault Detection and Isolation Using Locally Recurrent Neural Networks
ICAISC '08 Proceedings of the 9th international conference on Artificial Intelligence and Soft Computing
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
Towards Robustness in Neural Network Based Fault Diagnosis
International Journal of Applied Mathematics and Computer Science - Issues in Fault Diagnosis and Fault Tolerant Control
Local stability conditions for discrete-time cascade locally recurrent neural networks
International Journal of Applied Mathematics and Computer Science - Computational Intelligence in Modern Control Systems
Hi-index | 0.00 |
The paper deals with investigating approximation abilities of a special class of discrete-time dynamic neural networks. The networks considered are called locally recurrent globally feed-forward, because they are designed with dynamic neuron models which contain inner feedbacks, but interconnections between neurons are strict feed-forward ones like in the well-known multi-layer perceptron. The paper presents analytical results showing that a locally recurrent network with two hidden layers is able to approximate a state-space trajectory produced by any Lipschitz continuous function with arbitrary accuracy. Moreover, based on these results, the network can be simplified and transformed into a more practical structure needed in real world applications.