Biologically-Inspired Adaptive Learning: A Near Set Approach

The problem considered in this paper is how learning by machines can be influenced beneficially by various forms of learning by biological organisms. The solution to this problem is partially solved by considering considering a model of perception that is at the level of classes in a partition defined by a particular equivalence relation in an approximation space. This form of perception provides a basis for adaptive learning that has surprising acuity. Viewing approximation spaces as the formal counterpart of perception was suggested by Ewa Ortowska in 1982. This view of perception grew out the discovery of rough sets by Zdzistaw Pawlak during the early 1980s. The particular model of perception that underlies biologically-inspired learning is based on a near set approach, which considers classes of organisms with similar behaviours. In this paper, the focus is on learning by tropical fish called glowlight tetra (Hemigarmmus erythrozonus). Ethology (study of the comparative behaviour of organisms), in particular, provides a basis for the design of an artificial ecosystem useful in simulating the behaviour of fish. The contribution of this paper is a complete framework for an ethology-based study of adaptive learning defined in the context of nearness approximation spaces.

[1]  Rudi van Drunen,et al.  Localization of Random Pulse Point Sources Using Physically Implementable Search Algorithms , 2020, Optoelectronics, Instrumentation and Data Processing.

[2]  James F. Peters,et al.  Rough Ethology: Towards a Biologically-Inspired Study of Collective Behavior in Intelligent Systems with Approximation Spaces , 2005, Trans. Rough Sets.

[3]  James F. Peters,et al.  Image Pattern Recognition Using Near Sets , 2009, RSFDGrC.

[4]  James F. Peters,et al.  Approximation space for intelligent system design patterns , 2004, Eng. Appl. Artif. Intell..

[5]  Andrzej Skowron,et al.  Rudiments of rough sets , 2007, Inf. Sci..

[6]  J. Rissanen.  A UNIVERSAL PRIOR FOR INTEGERS AND ESTIMATION BY MINIMUM DESCRIPTION LENGTH , 1983 .

[7]  James F. Peters,et al.  Robotic Target Tracking with Approximation Space-Based Feedback During Reinforcement Learning , 2009, RSFDGrC.

[8]  J. Simpson,et al.  The Oxford English Dictionary , 1884 .

[9]  Ewa Orlowska,et al.  Semantics of Vague Concepts , 1985 .

[10]  P. Klopfer,et al.  The Foundations of Ethology , 1981 .

[11]  H. Evans.  The Study of Instinct , 1952 .

[12]  Jerry M. Mendel,et al.  Adaptive, learning, and pattern recognition systems : theory and applications , 1970 .

[13]  V. Stefflre,et al.  OTHER. The Herring Gull's World: A Study of Social Behavior of Birds. Niko Tinbergen , 1963 .

[14]  Monique Pavel,et al.  Fundamentals of pattern recognition , 1989 .

[15]  S. Balshine,et al.  Behaviour and physiology of fish , 2006 .

[16]  Andrzej Skowron,et al.  Nearness of Objects: Extension of Approximation Space Model , 2007, Fundam. Informaticae.

[17]  James F. Peters,et al.  Matching 2D Image Segments with Genetic Algorithms and Approximation Spaces , 2006, Trans. Rough Sets.

[18]  Andrzej Skowron,et al.  Nearness in Approximation Spaces , 2006 .

[19]  N. Tinbergen,et al.  The Herring Gull's World: A Study of the Social Behaviour of Birds , 1942 .

[20]  SOCIAL RELEASERS AND THE EXPERIMENTAL METHOD REQUIRED FOR THEIR STUDY , 2002 .

[21]  James F. Peters,et al.  Rough Ethograms: Study of Intelligent System Behavior , 2005, Intelligent Information Systems.

[22]  Jerzy W. Grzymala-Busse,et al.  Rough Sets , 1995, Commun. ACM.

[23]  Jerram L. Brown.  The evolution of behavior , 1975 .

[24]  James F. Peters,et al.  Approximation spaces in off-policy Monte Carlo learning , 2007, Eng. Appl. Artif. Intell..

[25]  Juan Pedro Vargas,et al.  Encoding of geometric and featural spatial information by goldfish (Carassius auratus). , 2004, Journal of comparative psychology.

[26]  J. Endler.  Signals, Signal Conditions, and the Direction of Evolution , 1992, The American Naturalist.

[27]  Xu Qing-yuan.  Generalized Approximation spaces Based on Inverse Serial Relation , 2004 .

[28]  Frank A. Beach,et al.  The herring gull's world. , 1955 .

[29]  James F. Peters,et al.  Near Sets. General Theory About Nearness of Objects , 2007 .

[30]  K. A. Semendyayev,et al.  Handbook of mathematics , 1985 .

[31]  Andrzej Skowron,et al.  Approximation Spaces and Information Granulation , 2004, Trans. Rough Sets.

[32]  James F. Peters,et al.  Toward Approximate Adaptive Learning , 2007, RSEISP.

[33]  Philip N. Lehner,et al.  Handbook of ethological methods , 1979 .

[34]  Oliver G. Selfridge,et al.  Some Themes and Primitives in Ill-Defined Systems , 1984 .

[35]  James F. Peters,et al.  Near Sets. Toward Approximation Space-Based Object Recognition , 2007, RSKT.

[36]  Z. Pawlak.  Classification of objects by means of attributes , 1981 .

[37]  Chris Watkins,et al.  Learning from delayed rewards , 1989 .

[38]  A. Hughes.  Oxford English Dictionary. , 2008, Isis; an international review devoted to the history of science and its cultural influences.

[39]  James F. Peters,et al.  Reinforcement Learning with Approximation Spaces , 2006, Fundam. Informaticae.

[40]  James F. Peters,et al.  Near Sets. Special Theory about Nearness of Objects , 2007, Fundam. Informaticae.

[41]  J. Busch,et al.  On the Optimality of the Binary Algorithm for the Jacobi Symbol , 2007, Fundam. Informaticae.

[42]  N. Tinbergen.  On aims and methods of Ethology , 2010 .

[43]  James F. Peters,et al.  Biologically-inspired adaptive learning control strategies: A rough set approach , 2007, Int. J. Hybrid Intell. Syst..