Knowledge network model with neurocognitive processing capabilities

Abstract The prime focus of scientists and the researchers in the field of intelligent systems is oriented to understand and replicate information processing functionalities of the human brain network. There have been continuous efforts to develop an intelligent knowledge system that incorporates the neuronal processes involved in cognition. In this paper the authors give some details of their unique work on the development of a knowledge system with information processing functionalities moving toward cognitive processing of the human brain, using intelligent links and nodes with processing capabilities. The existing knowledge systems connect only the pieces of information represented by nodes of a network and connect nodes using connectors, referred as edges. The edge is an attribute defining a relationship (e.g. isA, hasA) between the nodes. These edges lack cognitive properties, and the nodes lack functional processing to support efficient information transfer between nodes. The main objective of this paper is to provide an overview of the characteristics of a neurocognitive knowledge network model (NCKM) developed by the authors. NCKM is a knowledge network with nodes and links developed to provide methods that deal with the cognitive processes of the human brain, useful for efficient information processing. These cognitive processes provide self-directivity and learning within the network for intelligent knowledge retrieval. This work opens up a pathway to ingrain cognitive and neuronal characteristics for information processing into knowledge networks.

[1]  Ali A. Minai,et al.  Connectivity and thought : The influence of semantic network structure in a neurodynamical model of thinking , 2012 .

[2]  Huan Liu,et al.  Symbolic Representation of Neural Networks , 1996, Computer.

[3]  John R. Anderson.  ACT: A simple theory of complex cognition. , 1996 .

[4]  Eldon Y. Li.  Artificial neural networks and their business applications , 1994, Inf. Manag..

[5]  Teuvo Kohonen,et al.  Essentials of the self-organizing map , 2013, Neural Networks.

[6]  Peter Jackson,et al.  Introduction to expert systems , 1986 .

[7]  Gordon I. McCalla,et al.  What is knowledge representation , 1987 .

[8]  Peter Szolovits,et al.  What Is a Knowledge Representation? , 1993, AI Mag..

[9]  Ron Sun,et al.  Computational Models of Consciousness: An Evaluation , 1999 .

[10]  S. Grossberg.  Adaptive Resonance Theory , 2006 .

[11]  Ali A. Minai,et al.  Computational Models of Cognitive and Motor Control , 2015, Handbook of Computational Intelligence.

[12]  Lokendra Shastri,et al.  Connectionist mechanisms for cognitive control , 2005, Neurocomputing.

[13]  F. Attneave,et al.  The Organization of Behavior: A Neuropsychological Theory , 1949 .

[14]  Yiyu Yao,et al.  Perspectives on Cognitive Informatics and Cognitive Computing , 2010, Int. J. Cogn. Informatics Nat. Intell..

[15]  R. Sun.  Memory systems within a cognitive architecture , 2012 .

[16]  J. Byrne,et al.  More than synaptic plasticity: role of nonsynaptic plasticity in learning and memory , 2010, Trends in Neurosciences.

[17]  Gordon M. Shepherd,et al.  Introduction to Synaptic Circuits , 2004 .

[18]  Barry J. Wadsworth.  Piaget's Theory of Cognitive and Affective Development: Foundations of Constructivism , 2003 .

[19]  Michael A. Arbib,et al.  The handbook of brain theory and neural networks , 1995, A Bradford book.

[20]  J. Borst,et al.  How Do Short-Term Changes at Synapses Fine-Tune Information Processing? , 2012, The Journal of Neuroscience.

[21]  Charles L. A. Clarke,et al.  Information Retrieval - Implementing and Evaluating Search Engines , 2010 .

[22]  S. Grossberg.  The Link between Brain Learning, Attention, and Consciousness , 1999, Consciousness and Cognition.

[23]  P. Thagard,et al.  Mind: Introduction to Cognitive Science , 1996 .

[24]  P. Thagard,et al.  Mind: Introduction to cognitive science, 2nd ed. , 2005 .

[25]  Christof Koch,et al.  The role of single neurons in information processing , 2000, Nature Neuroscience.

[26]  Fernanda Botelho,et al.  A learning rule with generalized Hebbian synapses , 2002 .

[27]  J. Nadal,et al.  What can we learn from synaptic weight distributions? , 2007, Trends in Neurosciences.

[28]  J. Hopfield,et al.  Computing with neural circuits: a model. , 1986, Science.

[29]  D. Hassabis,et al.  Tracking the Emergence of Conceptual Knowledge during Human Decision Making , 2009, Neuron.

[30]  T. R. Gopalakrishnan Nair,et al.  Correlative Analysis of Data and Functions of Neuronal Synapse , 2013 .

[31]  Angelo Cangelosi,et al.  Integration of Speech and Action in Humanoid Robots: iCub Simulation Experiments , 2011, IEEE Transactions on Autonomous Mental Development.

[32]  Stephen Grossberg,et al.  Adaptive Resonance Theory , 2010, Encyclopedia of Machine Learning.

[33]  Shun-ichi Amari,et al.  Information geometry of the EM and em algorithms for neural networks , 1995, Neural Networks.

[34]  W. Pitts,et al.  A Logical Calculus of the Ideas Immanent in Nervous Activity (1943) , 2021, Ideas That Created the Future.

[35]  Nelson Morgan.  Programmable neurocomputing systems , 1998 .

[36]  J. Barnden.  Open-Ended Elaborations in Creative Metaphor , 2015 .

[37]  Nick Chater,et al.  Networks in Cognitive Science , 2013, Trends in Cognitive Sciences.

[38]  John R. Anderson,et al.  Using the ACT-R Cognitive Architecture in Combination With fMRI Data , 2015 .

[39]  Shun-ichi Amari.  Information Geometry and the EM Algorithm , 1994 .

[40]  Daniel J. Amit,et al.  Learning in Neural Networks with Material Synapses , 1994, Neural Computation.

[41]  O. Sporns.  Networks of the Brain , 2010 .

[42]  G. Palm,et al.  Towards a theory of cell assemblies , 2004, Biological Cybernetics.

[43]  T. R. Gopalakrishnan Nair,et al.  Knowledge Embedding and Retrieval Strategies in an Informledge System , 2011, ArXiv.

[44]  J. Flavell,et al.  Cognitive development: children's knowledge about the mind. , 1999, Annual review of psychology.

[45]  Jacek M. Zurada,et al.  Knowledge-based neurocomputing , 2000 .

[46]  T. R. Gopalakrishnan Nair,et al.  Creating intelligent linking for information threading in knowledge networks , 2011, 2011 Annual IEEE India Conference.

[47]  T. R. Gopalakrishnan Nair,et al.  Informledge System - A Modified Knowledge Network with Autonomous Nodes using Multi-lateral Links , 2010, KEOD.

[48]  Bing Liu,et al.  Web Data Mining: Exploring Hyperlinks, Contents, and Usage Data , 2006, Data-Centric Systems and Applications.

[49]  Yingxu Wang,et al.  A layered reference model of the brain , 2003, The Second IEEE International Conference on Cognitive Informatics, 2003. Proceedings..

[50]  M. Alexander,et al.  Principles of Neural Science , 1981 .

[51]  S. Schultz.  Principles of Neural Science, 4th ed. , 2001 .

[52]  Friedemann Pulvermüller,et al.  Recruitment and Consolidation of Cell Assemblies for Words by Way of Hebbian Learning and Competition in a Multi-Layer Neural Network , 2009, Cognitive Computation.

[53]  T. R. Gopalakrishnan Nair,et al.  Correlating and Cross-linking Knowledge Threads in Informledge System for Creating New Knowledge , 2014, KEOD.

[54]  Lokendra Shastri.  A Connectionist Approach to Knowledge Representation and Limited Inference , 1988 .

[55]  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.

[56]  Shushma Patel,et al.  A layered reference model of the brain (LRMB) , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[57]  S Grossberg,et al.  Some developmental and attentional biases in the contrast enhancement and short term memory of recurrent neural networks. , 1975, Journal of theoretical biology.