Design and analysis of a general recurrent neural network model for time-varying matrix inversion

By Yunong Zhang, Shuzhi Sam Ge. IEEE Transactions on Neural Networks, 2005

570 citations recorded by the source corpus.

Subfields: Control and Systems Engineering, Mechanical Engineering

View Paper: https://www.semanticscholar.org/paper/cc204d2aa7580b2886583486cebb8ae23e84887d

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Control and Systems Engineering

1. Shuai Li
2. Bo Liu
3. Sanfeng Chen

Citations in the corpus

• Accelerating a Recurrent Neural Network to Finite-Time Convergence for Solving Time-Varying Sylvester Equation by Using a Sign-Bi-power Activation Function (2012, background): “As revealed by simulations in [20,26], the following three nonlinear activation functions are observed to have superior convergence speed to the linear one: the bi-polar sigmoid activation function F(x) = 1−exp(−r x) 1+exp(−r x) with r > 2, the power activation function F(x) = xr with odd integer r ”