Stability properties of labeling recursive auto-associative memory
- 1 January 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 6 (6) , 1452-1460
- https://doi.org/10.1109/72.471363
Abstract
Labeling recursive auto-associative memory (LRAAM) is an extension of the RAAM model by Pollack (1990) to obtain distributed reduced representations of labeled directed graphs. In this paper some mathematical properties of LRAAM are discussed. Specifically, sufficient conditions on the asymptotical stability of the decoding process along a cycle of the encoded structure are given. LRAAM can be transformed into an analog Hopfield network with hidden units and an asymmetric connections matrix by connecting the output units with the input units. In this architecture encoded data can be accessed by content and different access procedures can be defined depending on the access key. Each access procedure corresponds to a particular constrained version of the recurrent network. The authors give sufficient conditions under which the property of asymptotical stability of a fixed point in one particular constrained version of the recurrent network can be extended to related fixed points in different constrained versions of the network. An example of encoding of a labeled directed graph on which the theoretical results are applied is given and discussed.Keywords
This publication has 15 references indexed in Scilit:
- Modular Labeling RAAMPublished by Springer Nature ,1995
- An Example of Neural Code: Neural Trees Implemented by LRAAMsPublished by Springer Nature ,1993
- An analog feedback associative memoryIEEE Transactions on Neural Networks, 1993
- On the analysis of dynamic feedback neural netsIEEE Transactions on Circuits and Systems, 1991
- BoltzCONS: Dynamic symbol structures in a connectionist networkArtificial Intelligence, 1990
- Tensor product variable binding and the representation of symbolic structures in connectionist systemsArtificial Intelligence, 1990
- A synthesis procedure for Hopfield's continuous-time associative memoryIEEE Transactions on Circuits and Systems, 1990
- Qualitative analysis of neural networksIEEE Transactions on Circuits and Systems, 1989
- On the stability, storage capacity, and design of nonlinear continuous neural networksIEEE Transactions on Systems, Man, and Cybernetics, 1988
- Neurons with graded response have collective computational properties like those of two-state neurons.Proceedings of the National Academy of Sciences, 1984