IEEE Transactions on Neural Networks · 1995 · 798 citations · 21 references
EngineeringComputer ScienceSystems EngineeringDynamical SystemsMachine LearningNeural EngineeringDynamic Systems AnalysisDynamic Systems ModelingNeural NetworksSystem IdentificationDynamic System IdentificationDynamical Systems ModelingDynamical Systems StabilityFeedforward Neural NetworksIdentification Of Dynamical SystemsNeural Network ModelingNonlinear Dynamical SystemsRecurrent Neural Networks
Recurrent neural networks have been applied to many engineering problems, yet developing efficient learning algorithms that also guarantee system stability remains difficult. The study investigates the approximation and learning properties of high‑order neural networks and their use for identifying dynamical systems. High‑order neural networks distribute dynamic components across the network via dynamic neurons, and the authors design and analyze identification schemes based on these architectures. With sufficient high‑order connections, the network can approximate any dynamical system.
Several continuous-time and discrete-time recurrent neural network models have been developed and applied to various engineering problems. One of the difficulties encountered in the application of recurrent networks is the derivation of efficient learning algorithms that also guarantee the stability of the overall system. This paper studies the approximation and learning properties of one class of recurrent networks, known as high-order neural networks; and applies these architectures to the identification of dynamical systems. In recurrent high-order neural networks, the dynamic components are distributed throughout the network in the form of dynamic neurons. It is shown that if enough high-order connections are allowed then this network is capable of approximating arbitrary dynamical systems. Identification schemes based on high-order network architectures are designed and analyzed.
21
Backpropagation through time: what it does and how to do it
Paul J. Werbos · Proceedings of the IEEE · 1990 · 4.9K citations
Adaptive filtering, prediction and control
Pétros Ioannou · Automatica · 1985 · 4.5K citations