Abstract
Learning is the highly complex and ongoing process in each and every stage of life to enrich our thought processes, in the same way our thought process is involved in the course of acquiring auxiliary knowledge with an existing knowledge. In this perspective human stands ahead on every stage of life, an important difference between intelligent autonomous applications and human intelligence is our ability to exploit common sense knowledge attained from a lifetime of learning and experiences to inform our decision-making and behavior. This allows humans to adapt easily to novel situations where intelligent autonomous systems fail in some cases due to lack of situation-specific rules and generalization capabilities.
In the ongoing research and development, most of the intelligent autonomous systems can do the task as expected, but still fails in the process of acquiring additional knowledge apart from the acquired knowledge. This is due to our way of learning methodologies, domain experience, and way of thought processes where we involved as a disciplinary, multidisciplinary, interdisciplinary and transdisciplinary approach of learning. In order for intelligent autonomous systems to exploit common sense knowledge in reasoning as humans do, understand domain specific basics, then, we need to provide them with human-like reasoning strategies.
In complex situation, in particular, representation of multiple domain knowledge to resolve the problem based on the situation. The domain knowledge should be adapted at multidimensional way or parallel or dynamic way of adapting the knowledge. This leads intelligent autonomous systems to use an alternative when it fails at the particular point of solving the problem, so for better result knowledge should be organized in the better way. Knowledge is dominantly organized in disciplines, as multidisciplinary and interdisciplinary research is developing at the boundaries of the scientific disciplines [8]. In this paper we compare transdisciplinary, interdisciplinary, multidisciplinary and non-disciplinary forms of knowledge representations and adopt transdisciplinary approach for intelligent autonomous systems with neural networks.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Kalashankar, Prasad, N.N.S.S.R.K.: An Innovative Future Classroom with an Intelligent Autonomous System – in a Transdisciplinary Approach. In: IETET – 2012, GIMT, Haryana, India (2012)
Merleau-Ponty, M.: Phenomenology of Perception. Routledge & Kegan Paul (1962)
Dreyfus, H.L.: What Computer’s can’t do – The Limits of Artificial Intelligence. Harper & Row, New York (1979)
Madhavan, R., Yu, W., Biggs, G., Schlenoff, C., Huang, H.M.: IEEE RAS Standing Committee for Standards Activities: History and Status Update
Journal of the Robotics Society of Japan, Special Issue on Activities of International Standards for Robot Technologies 29 (May 2011)
van den Besselaar, P., Heimeriks, G.: Disciplinary, Multidisciplinary, Interdisciplinary - Concepts and Indicators –8th CSI, Sydney (2011)
Russel, S., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice-Hall, Englewood Cliffs (1995)
Apgar, J.M., Argumedo, A., Allen, W.: Building Transdisciplinarity for Managing Complexity: Lessons from Indigenous Practice. International Journal of Interdisciplinary Social Sciences 4(5), 255–270 (2009)
Balke, W.-T., Mainzer, K.: Knowledge Representation and the Embodied Mind: Towards a Philosophy and Technology of Personalized Informatics, Germany
Mainzer, K.: Thinking in Complexity. In: The Computational Dynamics of Matter, Mind, and Mankind, 4th edn. Springer, New York (2004)
Mainzer, K.: KI - Künstliche Intelligenz. Grundlagen intelligenter Systeme. Wissenschaftliche Buchgesellschaft, Darmstadt, Germany (2003)
Cerar, J.: Master Thesis on Transdisciplinary Sustainability Development
Nicolescu, B.: The transdisciplinary evolution of learning – CIRET
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kalashankar, B.A., Prasad, N.N.S.S.R.K. (2013). Transdisciplinary Way of Knowledge Representation in Intelligent Autonomous Systems with Neural Networks. In: Kim, JH., Matson, E., Myung, H., Xu, P. (eds) Robot Intelligence Technology and Applications 2012. Advances in Intelligent Systems and Computing, vol 208. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-37374-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-642-37374-9_5
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-37373-2
Online ISBN: 978-3-642-37374-9
eBook Packages: EngineeringEngineering (R0)