A neurodynamical model for working memory

12 years 7 months ago
A neurodynamical model for working memory
Neurodynamical models of working memory (WM) should provide mechanisms for storing, maintaining, retrieving, and deleting information. Many models address 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. Key words: Recurrent Neural Networks, Echo State Networks, Working Memory, Attractor
Razvan Pascanu, Herbert Jaeger
Added 16 Sep 2011
Updated 16 Sep 2011
Type Journal
Year 2011
Where NN
Authors Razvan Pascanu, Herbert Jaeger
Comments (0)