Information storage and retrieval analysis of hierarchically coupled associative memories

This paper presents information storage and retrieval analysis as well as energy analysis of a multi-level or hierarchically coupled associative memory based on coupled generalised-brain-state-in-a-box (GBSB) neural networks. In this model, the memory processes are described as being organised functionally in hierarchical levels where higher levels coordinate sets of functions of the lower levels. We consider the case where lowest level subnetworks have predefined attractors, prior to imposing their association through imprinting synapses between them. Simulations are carried out using linearly independent (Li) and orthogonal vectors considering a wide range of parameters. The results obtained show that, even when the neural networks are weakly coupled, the system still presents a significant convergence to global patterns, mainly in orthogonal vectors.

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

[2]  A. Minai,et al.  Network capacity analysis for latent attractor computation , 2003, Network.

[3]  Jacek M. Zurada,et al.  An energy function-based design method for discrete hopfield associative memory with attractive fixed points , 2005, IEEE Transactions on Neural Networks.

[4]  Alessandro Treves,et al.  Short- and long-range connections in autoassociative memory , 1992 .

[5]  N. Kasabov,et al.  Evolving Intelligence in Humans and Machines: Integrative Evolving Connectionist Systems Approach , 2008, IEEE Computational Intelligence Magazine.

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

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

[8]  Peter Sussner,et al.  Gray-scale morphological associative memories , 2006, IEEE Transactions on Neural Networks.

[9]  Daniel J. Amit,et al.  Modeling brain function: the world of attractor neural networks, 1st Edition , 1989 .

[10]  Harvey J. Greenberg.  Equilibria of the brain-state-in-a-box (BSB) neural model , 1988, Neural Networks.

[11]  Dana Kulic,et al.  Incremental Learning and Memory Consolidation of Whole Body Human Motion Primitives , 2009, Adapt. Behav..

[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]  R. Golden.  The :20Brain-state-in-a-box Neural model is a gradient descent algorithm , 1986 .

[14]  David Sherrington,et al.  A feature retrieving attractor neural network , 1993 .

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

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

[17]  Gustavo Deco,et al.  Stochastic dynamics as a principle of brain function , 2009, Progress in Neurobiology.

[18]  Yaneer Bar-Yam,et al.  Dynamics Of Complex Systems , 2019 .

[20]  Henrique E. Borges,et al.  Space-vector structure based synthesis for hierarchically coupled associative memories , 2006, 2006 Ninth Brazilian Symposium on Neural Networks (SBRN'06).

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

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

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

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

[25]  E. Capaldi,et al.  The organization of behavior. , 1992, Journal of applied behavior analysis.

[26]  Frank Pasemann,et al.  Attractor Landscapes and Active Tracking: The Neurodynamics of Embodied Action , 2008, Adapt. Behav..

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

[28]  R. Golden.  Stability and optimization analyses of the generalized brain-state-in-a-box neural network model , 1993 .

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

[30]  Inman Harvey,et al.  Associative Learning on a Continuum in Evolved Dynamical Neural Networks , 2008, Adapt. Behav..

[31]  Philip Hider,et al.  Search goal revision in models of information retrieval , 2006, J. Inf. Sci..

[32]  Raymond Pavloski,et al.  The self-trapping attractor neural network-part II: properties of a sparsely connected model storing multiple memories , 2005, IEEE Transactions on Neural Networks.

[33]  Lynn Westbrook,et al.  Mental models: a theoretical overview and preliminary study , 2006, J. Inf. Sci..