Dynamic properties of an asymmetrical non-stationary neural net

Summary form only given, as follows. The authors have proposed a fully connected asymmetrical neural net with weight dynamics granting a continuous redefinition of its phase space. This is done by introducing two-site connectivities which are averages of two state products over a varying memory time τ. This system exhibits different behaviors (noiselike, chaotic, or stable) according to different values of its temporal control parameter. This is the ratio between the growth rate of τ and the velocity of the weight dynamics. In such a way, the probability distribution function of the states becomes nonstationary. Some hints were suggested to show how such a net is able to deal with second order statistics in particular for the recognition of moving objects in a noisy environment