Storage capacity of hierarchically coupled associative memories

This paper, taking as inspiration the ideas proposal for the TNGS (Theory of Neuronal Group Selection), presents a study of convergence capacity of two-level associative memories based on coupled Generalized-Brain-State-in-a-Box (GBSB) neural networks. In this model, the memory processes are described as being organized functionally in hierarchical levels, where the higher levels would coordinate sets of function of the lower levels. Simulations were carried out to illustrate the behaviour of the capacity of the system for a wide range of the system parameters considering linearly independent (LI) and orthogonal vectors. The results obtained show the relations amongst convergence, intensity and density of coupling.

[1]  J. P. Sutton,et al.  Neural models I: A hierarchical model of neocortical synaptic organization , 1988 .

[2]  Rogério M. Gomes,et al.  Energy Analysis of Hierarchically Coupled Generalized-Brain-State-inBox ( GBSB ) Neural Network , 2005 .

[3]  Stefen Hui,et al.  Synthesis of Brain-State-in-a-Box (BSB) based associative memories , 1994, IEEE Trans. Neural Networks.

[4]  Eric B. Baum,et al.  What is thought? , 2003 .

[5]  Stefen Hui,et al.  Learning and Forgetting in Generalized Brain-state-in-a-box (BSB) Neural Associative Memories , 1996, Neural Networks.

[6]  S. Smoliar.  Neural darwinism: The theory of neuronal group selection: Gerald M. Edelman, (Basic Books; New York, 1987); xxii + 371 pages , 1989 .

[7]  Igor Aleksander.  Beyond artificial intelligence , 2004, Nature.

[8]  David Barton,et al.  LEARNING IN DOING , 2005 .

[9]  Wolfgang Porod,et al.  Analysis and synthesis of a class of neural networks: variable structure systems with infinite grain , 1989 .

[10]  Antônio de Pádua Braga,et al.  A Model for Hierarchical Associative Memories via Dynamically Coupled GBSB Neural Networks , 2005, ICANN.

[11]  I. Guyon,et al.  Information storage and retrieval in spin-glass like neural networks , 1985 .

[12]  J J Hopfield,et al.  Neurons with graded response have collective computational properties like those of two-state neurons. , 1984, Proceedings of the National Academy of Sciences of the United States of America.

[13]  G. Edelman.  Neural Darwinism: The Theory Of Neuronal Group Selection , 1989 .

[14]  Stephen A. Ritz,et al.  Distinctive features, categorical perception, and probability learning: some applications of a neural model , 1977 .

[15]  Stefen Hui,et al.  Dynamical analysis of the brain-state-in-a-box (BSB) neural models , 1992, IEEE Trans. Neural Networks.

[16]  J. Farrell,et al.  Qualitative analysis of neural networks , 1989 .

[17]  L. Personnaz,et al.  Collective computational properties of neural networks: New learning mechanisms. , 1986, Physical review. A, General physics.