AN ORTHOGONAL LEARNING RULE FOR NULL-SPACE TRACKING WITH IMPLEMENTATION TO BLIND 2-CHANNEL IDENTIFICATION

This paper is motivated by the blind channel identification problem un der wireless communication environment, A temporal neural network is p resented whose synapses vector globally converges to the null space of an input data matrix for almost all initial conditions. When it is im plemented to the blind two-channel identification problem, it is shown . that, under certain mild conditions, it converges exactly to the cha nnel coefficients up to a scalar factor, Simulation shows that its con vergent speed is fast enough to be able to track time-varying channels under mobile communication environment. This temporal neural network is based on a new learning rule, called the orthogonal learning rule.