"Know Thyself" - Computational Self-Reflection in Intelligent Technical Systems

In many application domains, developers aim at building technical systems that can cope with the complexity of the world they are surrounded with, including other technical systems. Due to this complexity, system designers cannot explicitly foresee every possible situation "their" system will be confronted with at runtime. This resulted in solutions capable of self-adaptation at runtime. Future intelligent technical systems will have to go far beyond such a reactive solution - the general question is: How can systems themselves define new goals and new classes of goals in order to increase their own performance at runtime and without the need of human control or supervision? This paper introduces a definition of "computational self-reflection", proposes an architectural concept, and discusses the potential benefit by means of three exemplary application scenarios. Finally, building blocks to achieve self-reflection are discussed and a basic research agenda is drafted.

[1]  Bernhard Sick,et al.  Learning from others: Exchange of classification rules in intelligent distributed systems , 2012, Artif. Intell..

[2]  David Haussler,et al.  Exploiting Generative Models in Discriminative Classifiers , 1998, NIPS.

[3]  Jörg Hähner,et al.  Observation and Control of Organic Systems , 2011, Organic Computing.

[4]  Christian Jacob,et al.  Abstraction of agent interaction processes: Towards large-scale multi-agent models , 2013, Simul..

[5]  W. E. Fredrickson,et al.  Introspection , 2009 .

[6]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[7]  J. Cowan.  On becoming an innovative university teacher : reflection in action , 1998 .

[8]  Ming-Hsuan Yang,et al.  Adaptive Discriminative Generative Model and Its Applications , 2004, NIPS.

[9]  Nicholas L. Crookston,et al.  An aggregation algorithm for increasing the efficiency of population models , 1993 .

[10]  Brian Cantwell Smith,et al.  Procedural reflection in programming languages , 1982 .

[11]  Arthur P. Dempster,et al.  Upper and Lower Probabilities Induced by a Multivalued Mapping , 1967, Classic Works of the Dempster-Shafer Theory of Belief Functions.

[12]  Nelly Bencomo,et al.  Models@run.time , 2014, Lecture Notes in Computer Science.

[13]  S. Brookfield.  Critically reflective practice , 1998 .

[14]  Milan Rollo,et al.  An abstract architecture for computational reflection in multi-agent systems , 2005, IEEE/WIC/ACM International Conference on Intelligent Agent Technology.

[15]  Donald A. Sch.  The reflective practitioner: how professionals think in action , 1983 .

[16]  D. Kolb.  Experiential Learning: Experience as the Source of Learning and Development , 1983 .

[17]  Hartmut Schmeck,et al.  Organic Computing - A Paradigm Shift for Complex Systems , 2011, Organic Computing.

[18]  Mark F. Horstemeyer,et al.  Multiscale Modeling: A Review , 2009 .

[19]  Serge Kernbach,et al.  Collective Adaptive Systems: Challenges Beyond Evolvability , 2011, ArXiv.

[20]  Bernhard Sick,et al.  Let us know your decision: Pool-based active training of a generative classifier with the selection strategy 4DS , 2013, Inf. Sci..

[21]  J. Kiefer.  Conditional Confidence Statements and Confidence Estimators , 1977 .

[22]  Christopher Landauer,et al.  Reflection Processes Help Integrate Simultaneous Self-Optimization Processes , 2014, ARCS Workshops.

[23]  Christian Müller-Schloer,et al.  Organic computing: on the feasibility of controlled emergence , 2004, CODES+ISSS '04.

[24]  Christian Müller-Schloer,et al.  Quantitative Emergence -- A Refined Approach Based on Divergence Measures , 2010, 2010 Fourth IEEE International Conference on Self-Adaptive and Self-Organizing Systems.

[25]  Christopher Landauer.  Infrastructure for Studying Infrastructure , 2013, ESOS.

[26]  Jeffrey O. Kephart,et al.  The Vision of Autonomic Computing , 2003, Computer.

[27]  Pattie Maes,et al.  Concepts and experiments in computational reflection , 1987, OOPSLA '87.

[28]  Melanie Keller,et al.  The Music Of Life , 2016 .

[29]  Heather Goldsby,et al.  Automatically Generating Behavioral Models of Adaptive Systems to Address Uncertainty , 2008, MoDELS.

[30]  Bernd Kleinjohann,et al.  Increasing Learning Speed by Imitation in Multi-robot Societies , 2011, Organic Computing.

[31]  Jiddu Krishnamurti,et al.  On Self-Knowledge , 2002 .

[32]  Glenn Shafer,et al.  A Mathematical Theory of Evidence , 2020, A Mathematical Theory of Evidence.

[33]  Douglas C. Schmidt,et al.  Ultra-Large-Scale Systems: The Software Challenge of the Future , 2006 .

[34]  Jörg Denzinger,et al.  Self-organized Middle-Out Abstraction , 2011, IWSOS.

[35]  R. Nelsen.  An Introduction to Copulas , 1998 .

[36]  G. Gibbs.  Learning by doing: A guide to teaching and learning methods , 1988 .

[37]  Catherine Dibble,et al.  Dynamic Agent Compression , 2007, J. Artif. Soc. Soc. Simul..

[38]  Christine M. Anderson-Cook,et al.  Book review: quantitative risk management: concepts, techniques and tools, revised edition, by A.F. McNeil, R. Frey and P. Embrechts. Princeton University Press, 2015, ISBN 978-0-691-16627-8, xix + 700 pp. , 2017, Extremes.

[39]  Donald A. Schön,et al.  Organizational Learning: A Theory Of Action Perspective , 1978 .

[40]  Samee Ullah Khan,et al.  Advances in Intelligent Modelling and Simulation: Artificial Intelligence-Based Models and Techniques in Scalable Computing , 2012 .

[41]  Fabrizio Sestini.  Collective Awareness Platforms: Engines for Sustainability and Ethics , 2012, IEEE Technology and Society Magazine.

[42]  Weblog Wikipedia,et al.  In Wikipedia the Free Encyclopedia , 2005 .

[43]  Adel W. Sadek,et al.  Artificial Intelligence Applications in Transportation , 2007 .

[44]  Bernhard Sick,et al.  Techniques for knowledge acquisition in dynamically changing environments , 2012, TAAS.

[45]  Boleslaw K. Szymanski,et al.  Introduction to Scientific Data Mining: Direct Kernel Methods and Applications , 2004, Computationally Intelligent Hybrid Systems.

[46]  Jörg Hähner,et al.  Possibilities and limitations of decentralised traffic control systems , 2010, The 2010 International Joint Conference on Neural Networks (IJCNN).

[47]  Jörg Hähner,et al.  Organic Traffic Control , 2011, Organic Computing.

[48]  Seppo J. Ovaska,et al.  In Your Interest - Objective Interestingness Measures for a Generative Classifier , 2011, ICAART.

[49]  Bernhard Sick,et al.  Online Segmentation of Time Series Based on Polynomial Least-Squares Approximations , 2010, IEEE Transactions on Pattern Analysis and Machine Intelligence.