Control and Systems Engineering pp 289-311 | Cite as
Agencies of Intelligence: From the Macro to the Nano
- 1 Citations
- 1.5k Downloads
Abstract
‘Homo sapiens’ (Latin for ‘Wise Man’) is what we call our species. Wisdom and Intelligence stands at the center of how we define ourselves. But what is intelligence, and how does it influence an agent’s ability to face the world? In this chapter, we review an array of perspectives from the outer behavioral aspects of intelligence such as generalization, optimization and learning to its inner compositional that emphasizes intelligence in terms of networking and connectivity. Our journey will walk us through the concept of omnipotency where an entity has it all, knows it all, and does it all; to the nanopotency where the entity has little, knows little, and does little. From the original manifestation of the human dream to create the omnipotent being, we now come to its recent realization that perhaps less can be more. We will illustrate by sharing a few of our findings on traditionally hard problems such as robotics, urban traffic, fault detection and isolation, portfolio selection and judicial/medical decision making to the more evasive and humanly profound problems such as the atherosclerosis and cancer.
Keywords
Omnipotent Intelligence Learning Generalization Optimization Complex Systems AgentPreview
Unable to display preview. Download preview PDF.
References
- 1.Zadeh, L.A.: Fuzzy Sets. Information and Control 8, 338–353 (1965)CrossRefzbMATHMathSciNetGoogle Scholar
- 2.Zadeh, L.A.: Generalized Theory of Uncertainty (GTU) – Principal Concepts and Ideas. Computational Statistics & Data Analysis 51, 15–46 (2006)CrossRefzbMATHMathSciNetGoogle Scholar
- 3.Akbarzadeh-T., M.-R., Jamshidi, M.: Evolutionary Fuzzy Control of a Flexible Link. Journal of Intelligent Automation and Soft Computing 9(3), 181–214 (1997)Google Scholar
- 4.Hassanzadeh, H., Akbarzadeh-T., M.-R., Akbarzadeh-T., A.-R., Rezaei, A.: An Interval-valued Fuzzy Controller for Complex Dynamical Systems with Application to a 3PSP Parallel Robot. Fuzzy Sets and Systems 235, 83–100 (2014)CrossRefMathSciNetGoogle Scholar
- 5.Ghaemi., M., Akbarzadeh-T., M.-R.: Indirect Adaptive Interval Type-2 Fuzzy Sliding Mode Control for a Class of Uncertain Nonlinear Systems. Iranian Journal of Fuzzy Systems 11(5), 1–21 (2014)Google Scholar
- 6.Fartashtoloue, S.: Designing a Dynamic Growing General Type-2 Fuzzy Neural Controller for a Class of Nonlinear Systems with Experimental Implementation on a 3PSP Parallel Robot. M.S.Thesis, Ferdowsi University of Mashhad (2013)Google Scholar
- 7.Sabahi, F., Akbarzadeh-T., M.-R.: A qualified description of extended fuzzy logic. Information Sciences 244, 60–74 (2013)CrossRefMathSciNetGoogle Scholar
- 8.Sabahi, F., Akbarzadeh-T., M.-R.: Comparative Evaluation of Risk Factors in Coronary Heart Disease Based on Fuzzy Probability-Validity Modeling. Journal of Zanjan University of Medical Sciences and Health Services 22(91), 73–83 (2014)Google Scholar
- 9.Sabahi&, F., Akbarzadeh-T., M.-R.: Introducing Validity in Fuzzy Probabilities for Judicial Decision-Making. International Journal of Approximate Reasoning 55(6), 1383–1403 (2014)CrossRefMathSciNetGoogle Scholar
- 10.Tayarani, M.H., Akbarzadeh-T., M.-R.: Magnetic Inspired Optimization Algorithms: Operators and Structures. Swarm and Evolutionary Computation (accepted 2014)Google Scholar
- 11.Naghibi-S., M.-B., Akbarzadeh-T., M.-R., Javidi, H., Rajabi-M., H.: Application of Q-learning with Temperature Variation for Bidding Strategies in Market Based Power Systems. Journal of Energy Conversion and Management 47(11/12), 1529–1538 (2006)CrossRefGoogle Scholar
- 12.Aly El-Osery, J., Burge, M., Jamshidi, A., Saba, M., Fathi, M., Akbarzadeh-T., M.-R.: V-Lab: A Virtual Laboratory for Autonomous Agents – SLA-Based Learning Controllers. IEEE Transactions on Systems, Man and Cybernetics – Part B: Cybernetics 32(6), 791–803 (2002)CrossRefGoogle Scholar
- 13.Hecht-Nielsen, R.: Cogent confabulation. Neural Networks 18(2), 111–115 (2005)CrossRefGoogle Scholar
- 14.Soltani, A., Akbarzadeh-T., M.-R.: Confabulation-inspired Association Rule Mining for Rare and Frequent Itemsets. IEEE Transactions on Neural Networks 25(11), 2053–2064 (2014)CrossRefGoogle Scholar
- 15.Sotudeh-Chafi, M., Akbarzadeh-T., M.-R., Moavenian, M.: A Novel Soft Computing Approach to Component Fault Detection and Isolation of CNC X-axis Drive System. International Journal of Intelligent Automation and Soft Computing 16(2), 177–191 (2010)CrossRefGoogle Scholar
- 16.Akramizadeh, A., Akbarzadeh-T., M.R., Khademi, M.: Fuzzy Discrete Event System Modeling and Temporal Fuzzy Reasoning in Urban Traffic Control. In: Proceedings of the 2004 World Automation Congress and Fifth International Symposium on Intelligent Automation and Control, Seville, Spain, June 28-July 1 (2004)Google Scholar
- 17.Sengstacken, A.J., DeLaurentis, D.A., Akbarzadeh-T., M.R.: Optimization of Shared Autonomy Vehicle Control Architectures for Swarm Operations. IEEE Transactions on Systems, Man, and Cybernetics 40(4), 145–1157 (2010)Google Scholar
- 18.Hartmann, A.K., Weigt, M.: Phase Transitions in Combinatorial Optimization Problems, Basis, Algorithms and Statistical Mechanics. Wiley-VCH Verlag Co. (2005)Google Scholar
- 19.Vafaei Jahan, M., Akbarzadeh-T., M.R.: From Local Search to Global Conclusions: Migrating Spin Glass-based Distributed Portfolio Selection. IEEE Transactions on Evolutionary Computations (2009)Google Scholar
- 20.Rowhanimanesh, A., Akbarzadeh-T., M.-R.: Control of Low-Density Lipoprotein Concentration in the Arterial Wall by Proportional Drug-Encapsulated Nanoparticles. IEEE Transactions on Nanobioscience (2012)Google Scholar
- 21.Radyraz, N.: Bio-inspired Nanonetworks with Local Fuzzy Vision for Targeted Cancer Drug Delivery. M.S. Thesis, Islamic Azad University, Mashhad Branch (2014)Google Scholar