Perceptual Generalization and Context in a Network Memory Inspired Long-Term Memory for Artificial Cognition

In the framework of open-ended learning cognitive architectures for robots, this paper deals with the design of a Long-Term Memory (LTM) structure that can accommodate the progressive acquisition of experience-based decision capabilities, or what different authors call "automation" of what is learnt, as a complementary system to more common prospective functions. The LTM proposed here provides for a relational storage of knowledge nuggets given the form of artificial neural networks (ANNs) that is representative of the contexts in which they are relevant in a configural associative structure. It also addresses the problem of continuous perceptual spaces and the task- and context-related generalization or categorization of perceptions in an autonomous manner within the embodied sensorimotor apparatus of the robot. These issues are analyzed and a solution is proposed through the introduction of two new types of knowledge nuggets: P-nodes representing perceptual classes and C-nodes representing contexts. The approach is studied and its performance evaluated through its implementation and application to a real robotic experiment.

[1]  Chu Kiong Loo,et al.  Developmental Approach for Behavior Learning Using Primitive Motion Skills , 2017, Int. J. Neural Syst..

[2]  J. Pearce.  A model for stimulus generalization in Pavlovian conditioning. , 1987, Psychological review.

[3]  Saeid Sanei,et al.  Deep Neural Architectures for Mapping Scalp to Intracranial EEG , 2018, Int. J. Neural Syst..

[4]  Mathilde Petton,et al.  Neural Activity Elicited by a Cognitive Task can be Detected in Single-Trials with Simultaneous Intracerebral EEG-fMRI Recordings , 2017, Int. J. Neural Syst..

[5]  Walter Schneider,et al.  Controlled and Automatic Human Information Processing: 1. Detection, Search, and Attention. , 1977 .

[6]  Marco Mirolli,et al.  Phasic dopamine as a prediction error of intrinsic and extrinsic reinforcements driving both action acquisition and reward maximization: A simulated robotic study , 2013, Neural Networks.

[7]  Ron Sun,et al.  The importance of cognitive architectures: an analysis based on CLARION , 2007, J. Exp. Theor. Artif. Intell..

[8]  Zhang Yi,et al.  A New Delay Connection for Long Short-Term Memory Networks , 2017, Int. J. Neural Syst..

[9]  Harold Gulliksen,et al.  A theory of learning and transfer: II , 1938 .

[10]  A. Carassa,et al.  Representational redescription and cognitive architectures , 1994, Behavioral and Brain Sciences.

[11]  Andrei Paun,et al.  Simplified and Yet Turing Universal Spiking Neural P Systems with Communication on Request , 2018, Int. J. Neural Syst..

[12]  J. Pearce.  Similarity and Discrimination: A Selective Review and a Connectionist Model , 1994 .

[13]  R. R. Miller,et al.  What's elementary about associative learning? , 1997, Annual review of psychology.

[14]  G. Sandini,et al.  The iCub cognitive architecture: Interactive development in a humanoid robot , 2007, 2007 IEEE 6th International Conference on Development and Learning.

[15]  W. Newsome,et al.  Context-dependent computation by recurrent dynamics in prefrontal cortex , 2013, Nature.

[16]  Steven L. Bressler,et al.  Past Makes Future: Role of pFC in Prediction , 2015, Journal of Cognitive Neuroscience.

[17]  Eugene M. Izhikevich,et al.  Simple model of spiking neurons , 2003, IEEE Trans. Neural Networks.

[18]  John R Anderson,et al.  An integrated theory of the mind. , 2004, Psychological review.

[19]  Andrés Faiña,et al.  Multilevel Darwinist Brain (MDB): Artificial Evolution in a Cognitive Architecture for Real Robots , 2010, IEEE Transactions on Autonomous Mental Development.

[20]  N. Mackintosh.  A Theory of Attention: Variations in the Associability of Stimuli with Reinforcement , 1975 .

[21]  Giulio Sandini,et al.  Prospection in Cognition: The Case for Joint Episodic-Procedural Memory in Cognitive Robotics , 2015, Front. Robot. AI.

[22]  Stuart C. Shapiro,et al.  Anchoring in a grounded layered architecture with integrated reasoning , 2003, Robotics Auton. Syst..

[23]  Viviana Patricia,et al.  Propuesta didáctica para la apropiación del proceso lectoescritor en educación básica primaria centrado en el desarrollo psicomotriz , 2020 .

[24]  E. Kehoe,et al.  Summation and configuration in patterning schedules with the rat and rabbit , 1985 .

[25]  D E Kieras,et al.  A computational theory of executive cognitive processes and multiple-task performance: Part 1. Basic mechanisms. , 1997, Psychological review.

[26]  Pierre-Yves Oudeyer,et al.  What is Intrinsic Motivation? A Typology of Computational Approaches , 2007, Frontiers Neurorobotics.

[27]  T. Martin McGinnity,et al.  Intrinsically motivated learning systems based on biologically-inspired novelty detection , 2015, Robotics Auton. Syst..

[28]  Ben Goertzel,et al.  OpenCogPrime: A cognitive synergy based architecture for artificial general intelligence , 2009, 2009 8th IEEE International Conference on Cognitive Informatics.

[29]  L. R. Peterson,et al.  Short-term retention of individual verbal items. , 1959, Journal of experimental psychology.

[30]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[31]  Linqiang Pan,et al.  Spiking Neural P Systems With Communication on Request and Mute Rules , 2017, IEEE Transactions on Parallel and Distributed Systems.

[32]  Randall W Engle,et al.  Working memory, short-term memory, and general fluid intelligence: a latent-variable approach. , 1999, Journal of experimental psychology. General.

[33]  Richard C. Atkinson,et al.  Human Memory: A Proposed System and its Control Processes , 1968, Psychology of Learning and Motivation.

[34]  Boguslaw Cyganek,et al.  Image recognition with deep neural networks in presence of noise - Dealing with and taking advantage of distortions , 2017, Integr. Comput. Aided Eng..

[35]  H. Simon,et al.  Why are some problems hard? Evidence from Tower of Hanoi , 1985, Cognitive Psychology.

[36]  Tony Belpaeme,et al.  A review of long-term memory in natural and synthetic systems , 2012, Adapt. Behav..

[37]  H. Simon,et al.  The mind's eye in chess. , 1973 .

[38]  Manuel Roveri,et al.  An Ensemble Approach for Cognitive Fault Detection and Isolation in Sensor Networks , 2017, Int. J. Neural Syst..

[39]  E. Kehoe.  A layered network model of associative learning: learning to learn and configuration. , 1988, Psychological review.

[40]  J. Fuster.  Cortical dynamics of memory. , 1998, International journal of psychophysiology : official journal of the International Organization of Psychophysiology.

[41]  Joaquín M. Fuster,et al.  Cortex and Memory: Emergence of a New Paradigm , 2009, Journal of Cognitive Neuroscience.

[42]  Richard J. Duro,et al.  Considering Memory Networks in the LTM Structure of the Multilevel Darwinist Brain , 2016, GECCO.

[43]  K. A. Ericsson,et al.  Long-term working memory. , 1995, Psychological review.

[44]  Juan Carlos,et al.  Efecto de las señales visuales y la calidad del néctar en la toma de decisiones económicas en Apis mellifera , 2020 .

[45]  J. Pearce.  Evaluation and development of a connectionist theory of configural learning , 2002, Animal learning & behavior.

[46]  J. Pearce,et al.  A model for Pavlovian learning: Variations in the effectiveness of conditioned but not of unconditioned stimuli. , 1980 .

[47]  M. Just,et al.  From the Selectedworks of Marcel Adam Just the Organization of Thinking: What Functional Brain Imaging Reveals about the Neuroarchitecture of Complex Cognition , 2022 .