Encoding Labeled Graphs by Labeling RAAM

Neural Information Processing Systems 

In this paper we propose an extension to the RAAM by Pollack. Data encoded in an LRAAM can be accessed by pointer as well as by content. Direct access by content can be achieved by transform(cid:173) ing the encoder network of the LRAAM into an analog Hopfield network with hidden units. Different access procedures can be defined depending on the access key. Sufficient conditions on the asymptotical stability of the associated Hopfield network are briefly introduced.