A new model of associative memories network

An associative memory (AM) is a special kind of neural network that only allows associating an output pattern with an input pattern. However, some problems require associating several output patterns with a unique input pattern. Classical associative and neural models cannot solve this simple task. In this paper we propose a new network composed of several AMs aimed to solve this problem. By using this new model, AMs can be able to associate several output patterns with a unique input pattern. We test the accuracy of the proposal with a database of real images. We split this database of images into four collections of images and then we trained the network of AMs. During training we associate an image of a collection with the rest of the images belonging to the same collection. Once trained the network we expected to recover a collection of images by using as an input pattern any image belonging to the collection.

[1]  Peter Sussner,et al.  Generalizing Operations of Binary Autoassociative Morphological Memories Using Fuzzy Set Theory , 2003, Journal of Mathematical Imaging and Vision.

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

[3]  I Reinvang.  Amnestic disorders and their role in cognitive theory. , 1998, Scandinavian journal of psychology.

[4]  Juan Humberto Sossa Azuela,et al.  New Associative Memories to Recall Real-Valued Patterns , 2004, CIARP.

[5]  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.

[6]  Juan Humberto Sossa Azuela,et al.  Transforming Fundamental Set of Patterns to a Canonical Form to Improve Pattern Recall , 2004, IBERAMIA.

[7]  Katica D Jovanova-Nesic,et al.  The Neuronal and Immune Memory Systems as Supervisors of Neural Plasticity and Aging of the Brain: From Phenomenology to Coding of Information , 2005, Annals of the New York Academy of Sciences.

[8]  Gerhard X. Ritter,et al.  Reconstruction of Patterns from Noisy Inputs Using Morphological Associative Memories , 2003, Journal of Mathematical Imaging and Vision.

[9]  Terrence J Sejnowski,et al.  Communication in Neuronal Networks , 2003, Science.

[10]  M. Kutas,et al.  Brain potentials during reading reflect word expectancy and semantic association , 1984, Nature.

[11]  C. Price.  The anatomy of language: contributions from functional neuroimaging , 2000, Journal of anatomy.

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

[13]  Karl Steinbuch,et al.  Die Lernmatrix , 2004, Kybernetik.