Typical attractor neural networks (ANN) used to model associative memories behave like disordered systems, as the asymptotic state of their dynamics depends in a crucial (and often unpredictable) way on the chosen initial state. In this paper we suggest that this circumstance occurs only when we deal with such ANN as isolated systems. If we introduce a suitable control, coming from the interaction with a reactive external environment, then the disordered nature of ANN dynamics can be reduced, or even disappear. To support this claim we resort to a simple example based on a version of Hopfield autoassociative memory model interacting with an external environment which modifies the network weights as a function of the equilibrium state coming from retrieval dynamics.
Feedback control tames disorder in attractor neural networks
PENNA, MARIA PIETRONILLA;
2009-01-01
Abstract
Typical attractor neural networks (ANN) used to model associative memories behave like disordered systems, as the asymptotic state of their dynamics depends in a crucial (and often unpredictable) way on the chosen initial state. In this paper we suggest that this circumstance occurs only when we deal with such ANN as isolated systems. If we introduce a suitable control, coming from the interaction with a reactive external environment, then the disordered nature of ANN dynamics can be reduced, or even disappear. To support this claim we resort to a simple example based on a version of Hopfield autoassociative memory model interacting with an external environment which modifies the network weights as a function of the equilibrium state coming from retrieval dynamics.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
