The unit feedback recursive neural network model which is widely used at present has been analyzed. It makes the unit feedback recursive neural network have the same dynamic process and time delay characteristic. The applications of the unit recursive neural networks are limited. For its shortcomings, we proposed another state feedback recursive neuron model, and their state feedback recursive neural network model. In this neural network model, the static weight of the neural network explained the static transmission performance, and the state feedback recursive factor indicated the dynamic performance of neural networks, the different state feedback recursion factor indicated the dynamic process time of the different systems. Therefore, the state-feedback neural network dynamic characteristics and learning strategies, which have great theoretical and application significance, are studied.
[1]
Dai Yi.
Structure of recurrent neural networks
,
2004
.
[2]
Sammy Siu,et al.
Analysis of the Initial Values in Split-Complex Backpropagation Algorithm
,
2008,
IEEE Transactions on Neural Networks.
[3]
Liu Sheng,et al.
A Normalized Adaptive Training of Recurrent Neural Networks With Augmented Error Gradient
,
2008,
IEEE Transactions on Neural Networks.
[4]
Yeng Chai Soh,et al.
Robust Adaptive Gradient-Descent Training Algorithm for Recurrent Neural Networks in Discrete Time Domain
,
2008,
IEEE Transactions on Neural Networks.
[5]
LI Guo-dong.
Multivariable Adaptive PID-like Neural Network Controller and Its Design Method
,
2006
.
[6]
XI Jian-hui.
Learning the trajectories of periodic attractor using recurrent neural network
,
2006
.