Neurodynamical models of working memory (WM) should provide mechanisms
for storing, maintaining, retrieving, and deleting information. Many models ad-
dress only a subset of these aspects. Here we present a rather simple WM model where all of these performance modes are trained into a recurrent neural network (RNN) of the Echo State Network (ESN) type. The model is demonstrated on a bracket level parsing task with a stream of rich and noisy graphical script input. In terms of nonlinear dynamics, memory states correspond, intuitively, to attractors in an input-driven system. As a supplementary contribution, the article proposes a rigorous formal framework to describe such attractors, generalizing from the standard definition of attractors in autonomous (input-free) dynamical systems.
| 
