Spatial Concept Learning: A Spiking Neural Network Implementation in Virtual and Physical Robots

This paper proposes an artificial spiking neural network (SNN) sustaining the cognitive abstract process of spatial concept learning, embedded in virtual and real robots. Based on an operant conditioning procedure, the robots learn the relationship of horizontal/vertical and left/right visual stimuli, regardless of their specific pattern composition or their location on the images. Tests with novel patterns and locations were successfully completed after the acquisition learning phase. Results show that the SNN can adapt its behavior in real time when the rewarding rule changes.

[1]  Angelo Cangelosi,et al.  A review of abstract concept learning in embodied agents and robots , 2018, Philosophical Transactions of the Royal Society B: Biological Sciences.

[2]  A. Wright.  Concept Learning and Learning Strategies , 1997 .

[3]  Wofgang Maas,et al.  Networks of spiking neurons: the third generation of neural network models , 1997 .

[4]  H. Markram,et al.  Regulation of Synaptic Efficacy by Coincidence of Postsynaptic APs and EPSPs , 1997, Science.

[5]  Adrian G. Dyer,et al.  Conceptualization of relative size by honeybees , 2014, Front. Behav. Neurosci..

[6]  Kent D. Bodily,et al.  Issues in the Comparative Cognition of Abstract-Concept Learning. , 2007, Comparative cognition & behavior reviews.

[7]  Y. Dan,et al.  Spike timing-dependent plasticity: a Hebbian learning rule. , 2008, Annual review of neuroscience.

[8]  M. Giurfa.  Cognition with few neurons: higher-order learning in insects , 2013, Trends in Neurosciences.

[9]  M. Giurfa,et al.  Conceptualization of above and below relationships by an insect , 2011, Proceedings of the Royal Society B: Biological Sciences.

[10]  A. Wright,et al.  Generalization hypothesis of abstract-concept learning: learning strategies and related issues in Macaca mulatta, Cebus apella, and Columba livia. , 2007, Journal of comparative psychology.

[11]  Wolfgang Maass,et al.  Networks of Spiking Neurons: The Third Generation of Neural Network Models , 1996, Electron. Colloquium Comput. Complex..

[12]  M. Srinivasan,et al.  The concepts of ‘sameness’ and ‘difference’ in an insect , 2001, Nature.

[13]  J. Bachevalier,et al.  Mechanisms of same/different abstract-concept learning by rhesus monkeys (Macaca mulatta). , 2002, Journal of experimental psychology. Animal behavior processes.

[14]  R. Menzel.  The honeybee as a model for understanding the basis of cognition , 2012, Nature Reviews Neuroscience.

[15]  T. Toyoizumi,et al.  Learning with three factors: modulating Hebbian plasticity with errors , 2017, Current Opinion in Neurobiology.

[16]  M. Giurfa,et al.  Simultaneous mastering of two abstract concepts by the miniature brain of bees , 2012, Proceedings of the National Academy of Sciences.

[17]  A. Wright,et al.  Same/different abstract-concept learning by pigeons. , 2006, Journal of experimental psychology. Animal behavior processes.

[18]  M. Giurfa,et al.  Conceptual learning by miniature brains , 2013, Proceedings of the Royal Society B: Biological Sciences.

[19]  G. Bi,et al.  Synaptic Modifications in Cultured Hippocampal Neurons: Dependence on Spike Timing, Synaptic Strength, and Postsynaptic Cell Type , 1998, The Journal of Neuroscience.

[20]  Jeffrey L. Krichmar,et al.  Neurorobotics—A Thriving Community and a Promising Pathway Toward Intelligent Cognitive Robots , 2018, Front. Neurorobot..

[21]  Roger K. R. Thompson,et al.  Concept learning in animals. , 2008 .

[22]  Pierre Poirier,et al.  AI-SIMCOG: a simulator for spiking neurons and multiple animats’ behaviours , 2009, Neural Computing and Applications.

[23]  Henning Sprekeler,et al.  Functional Requirements for Reward-Modulated Spike-Timing-Dependent Plasticity , 2010, The Journal of Neuroscience.

[24]  A. Avarguès-Weber,et al.  Sameness/difference spiking neural circuit as a relational concept precursor model: A bio-inspired robotic implementation , 2017, BICA 2017.

[25]  L. Chittka,et al.  Animal Cognition: Concepts from Apes to Bees , 2011, Current Biology.

[26]  Clint J. Perry,et al.  Invertebrate learning and cognition: relating phenomena to neural substrate. , 2013, Wiley interdisciplinary reviews. Cognitive science.

[27]  Wulfram Gerstner,et al.  SPIKING NEURON MODELS Single Neurons , Populations , Plasticity , 2002 .

[28]  Edward A Wasserman,et al.  Associative Concept Learning in Animals Recommended Citation , 2022 .