Binary autoassociative morphological memories derived from the kernel method and the dual kernel method

Morphological associative memories (MAMs) belong to the class of morphological neural networks. The recording scheme used in the original MAM models is similar to the correlation recording recipe. Recording is achieved by means of a maximum (M/sub XY/ model) or minimum (W/sub XY/ model) of outer products. Notable features of autoassociative morphological memories (AMMs) include optimal absolute storage capacity and one-step convergence. The fixed points of AMMs can be characterized exactly in terms of the original patterns. Unfortunately, AMM fixed points include a large number of spurious memories. A combination of the M/sub XX/ model and the kernel method yields another binary AMM model. In this paper, we also introduce a dual kernel method. A new, dual model is given by a combination of the W/sub XX/ and the dual kernel method. The new AMM models exhibit better error correction capabilities than M/sub XX/ and W/sub XX/ and a reduced number of spurious memories, which can be easily described in terms of the fundamental memories. Finally, we present yet another pair of AMMs with very similar properties. Although these models are also derived from the kernel or dual kernel methods, their construction depends on less restrictive conditions.

[1]  Mohamad H. Hassoun.  Dynamic associative neural memories , 1993 .

[2]  Peter Sussner,et al.  Morphological bidirectional associative memories , 1999, Neural Networks.

[3]  Bogdan Raducanu,et al.  On the application of morphological heteroassociative neural networks , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[4]  Stella N. Batalama,et al.  An efficient learning algorithm for associative memories , 2000, IEEE Trans. Neural Networks Learn. Syst..

[5]  Peter Sussner,et al.  Associative morphological memories based on variations of the kernel and dual kernel methods , 2003, Neural Networks.

[6]  Paul D. Gader,et al.  Morphological regularization neural networks , 2000, Pattern Recognit..

[7]  Bogdan Raducanu,et al.  Morphological neural networks for robust visual processing in mobile robotics , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[8]  Peter Sussner,et al.  Morphological associative memories , 1998, IEEE Trans. Neural Networks.

[9]  Peter Sussner,et al.  An introduction to morphological neural networks , 1996, Proceedings of 13th International Conference on Pattern Recognition.

[10]  G. Palm,et al.  On associative memory , 2004, Biological Cybernetics.

[11]  Peter Sussner.  Fixed points of autoassociative morphological memories , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[12]  Peter Sussner,et al.  Observations on morphological associative memories and the kernel method , 2000, Neurocomputing.

[13]  Kaoru Nakano,et al.  Associatron-A Model of Associative Memory , 1972, IEEE Trans. Syst. Man Cybern..

[14]  James A. Anderson,et al.  A simple neural network generating an interactive memory , 1972 .

[15]  J Nagumo,et al.  [A model of associative memory]. , 1972, Iyo denshi to seitai kogaku. Japanese journal of medical electronics and biological engineering.

[16]  R. Cuninghame-Green.  Minimax Algebra and Applications , 1994 .

[17]  Dimitris A. Pados,et al.  A feedforward bidirectional associative memory , 2000, IEEE Trans. Neural Networks Learn. Syst..

[18]  Paul D. Gader,et al.  Morphological shared-weight networks with applications to automatic target recognition , 1997, IEEE Trans. Neural Networks.

[19]  Santosh S. Venkatesh,et al.  The capacity of the Hopfield associative memory , 1987, IEEE Trans. Inf. Theory.

[20]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[21]  BART KOSKO,et al.  Bidirectional associative memories , 1988, IEEE Trans. Syst. Man Cybern..

[22]  Bogdan Raducanu,et al.  Morphological neural networks for vision based self-localization , 2001, Proceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (Cat. No.01CH37164).

[23]  Teuvo Kohonen,et al.  Correlation Matrix Memories , 1972, IEEE Transactions on Computers.