No Access

Cultural Algorithms as a Framework for the Design of Trustable Evolutionary Algorithms

Anas Al-Tirawi

Department of Computer Science, Wayne State University, Detroit, Michigan 48201, USA

E-mail Address: aaltirawi@wayne.edu

Search for more papers by this author

and

Robert G. Reynolds

Department of Computer Science, Wayne State University, Detroit, Michigan 48201, USA

Museum of Anthropological Archaeology, University of Michigan, Ann Arbor, Michigan 48201, USA

E-mail Address: reynolds@cs.wayne.edu

Search for more papers by this author

https://doi.org/10.1142/S1793351X22400062Cited by:0 (Source: Crossref)

This article is part of the issue:

Special Issue: Selected Papers from the 3rd IEEE International Conference on Transdisciplinary Artificial Intelligence (TransAI 2021)
Guest Editors: Gary B. Glesener and Julienne A. Greer

Abstract

One of the major challenges facing Artificial Intelligence in the future is the design of trustworthy algorithms. The development of trustworthy algorithms will be a key challenge in Artificial Intelligence for years to come. Cultural Algorithms (CAs) are viewed as one framework that can be employed to produce a trustable evolutionary algorithm. They contain features to support both sustainable and explainable computation that satisfy requirements for trustworthy algorithms proposed by Cox [Nine experts on the single biggest obstacle facing AI and algorithms in the next five years, Emerging Tech Brew, January 22, 2021]. Here, two different configurations of CAs are described and compared in terms of their ability to support sustainable solutions over the complete range of dynamic environments, from static to linear to nonlinear and finally chaotic. The Wisdom of the Crowds method was selected for the one configuration since it has been observed to work in both simple and complex environments and requires little long-term memory. The Common Value Auction (CVA) configuration was selected to represent those mechanisms that were more data centric and required more long-term memory content.

Both approaches were found to provide sustainable performance across all the dynamic environments tested from static to chaotic. Based upon the information collected in the Belief Space, they produced this behavior in different ways. First, the topologies that they employed differed in terms of the “in degree” for different complexities. The CVA approach tended to favor reduced “indegree/outdegree”, while the WM exhibited a higher indegree/outdegree in the best topology for a given environment. These differences reflected the fact the CVA had more information available for the agents about the network in the Belief Space, whereas the agents in the WM had access to less available knowledge. It therefore needed to spread the knowledge that it currently had more widely throughout the population.

Keywords:

References

1. F. Hayden, Nine experts on the single biggest obstacle facing AI and algorithms in the next five years, Emerging Tech Brew, January 22, 2021. Google Scholar
2. R. G. Reynolds , Algorithms: Tools for the Engineering of Social Intelligence into Complex Cultural Systems (Wiley-IEEE Press, 2020). Google Scholar
3. R. G. Reynolds , Cultural Algorithms: Tools for the Engineering of Social Intelligence into Complex Cultural Systems (Wiley-IEEE Press, 2020). Crossref, Google Scholar
4. W. Sverdlik, R. G. Reynolds and E. Zannoni , HYBAL: A self-tuning algorithm for concept learning in highly autonomous systems, Proceedings of the Third Annual Conference of AI, Simulation, and Planning in High Autonomy Systems ‘Integrating Perception, Planning and Action’, (1992). Crossref, Google Scholar
5. J. Husdal , Robustness and Flexibility as Option to Reduce Uncertainty and Risk (Molde University College, Molde, Norway, 2004). Google Scholar
6. R. G. Reynolds , An overview of cultural algorithms, in New Ideas in Optimization, eds. D. Corne, F. Glover and M. Dorigo (McGraw Hill Press, 1999), pp. 367–378. Google Scholar
7. C. Coello, C. Artemio and T. Ma Gaudalupe Castillo , in Handbook of AI-Based Methuristics, Ch 8: Cultural Algorithm for Optimization, eds. A. J. Kulikarni and P. Siarry (CRC Press, 2021). Google Scholar
8. R. G. Reynolds , An Adaptive Computer Model of the Evolution of Agriculture (University of Michigan, Ann Arbor, MI, 1979). Google Scholar
9. T. W. Jayyousi, Bringing to life an ancient urban center at Monte Albán, Mexico: Exploiting the synergy between the micro, meso, and macro levels in a complex system, thesis, Wayne State Univerity, Detroit, MI (2012). Google Scholar
10. W. Sverdlik, R. G. Reynolds and E. Zannoni, HYBAL: A Self-Tuning Algorithm for Concept Learning in Highly Autonomous Systems (1992). Google Scholar
11. H. A. Al-Shehri, Evolution-based decision tree optimization using cultural algorithms, thesis, Wayne State University, Detroit, MI (1997). Google Scholar
12. R. G. Reynolds and D. Ostrowski , Knowledge-based software testing agent using evolutionary learning with cultural algorithms, in Proc. IEEE Congress on Evolutionary Computation, 1999. Google Scholar
13. M. Z. Ali, N. H. Awad, P. N. Suganthan, R. M. Duwairi and R. G. Reynolds , A novel hybrid cultural algorithms framework with trajectory-based search for global numerical optimization, Inf. Sci. 334(C) (2016) 219–249. Crossref, Web of Science, Google Scholar
14. F. Waris and R. G. Reynolds , Optimizing AI pipelines: A game-theoretic cultural algorithms approach, IEEE Congress on Evolutionary Computation (CEC), 2018, pp. 1–10. Crossref, Google Scholar
15. A. Al-Tirawi and R. G. Reynolds , Maintaining knowledge distribution system’s sustainability using common value auctions, in Association for the Advancement of Artificial Intelligence (AAAI), 2019. Google Scholar
16. A. Al-Tirawi and R. G. Reynolds , Sustainable learning in cultural algorithms using common value auctions, in Int. Conf. Computational Science and Computational Intelligence (CSCI), 2019. Crossref, Google Scholar
17. X. Che, M. Z. Ali and R. G. Reynolds , Robust evolution optimization at the edge of chaos: Commercialization of culture algorithms, IEEE Congress on Evolutionary Computation, 2010, pp. 3–4. Crossref, Google Scholar
18. R. G. Reynolds, B. Peng and X. Che , Knowledge swarms generating emergent social structure in dynamic enviroments, in Proc. Agent Conf. Generative Social Processes, Models, and Mechanims, 2005, pp. 6–7. Google Scholar
19. B. Peng, Knowledge swarms in cultural algorithms for dynamic environments, Ph.D. thesis, Wayne State University, Detroit, MI (2005). Google Scholar
20. R. G. Reynolds and M. Ali , Embedding a social fabric component into cultural algorithms toolkit for an enhanced knowledge-driven engineering optimization, Int. J. Intell. Comput. Cybernet. 1(4) (2008) 356–378. Google Scholar
21. R. G. Reynolds and M. Ali , The social fabric approach as an approach to knowledge integration in Cultural Algorithms, in IEEE Congress on Evolutionary Computation, 2009. Google Scholar
22. X. Che, M. Z. Ali and R. G. Reynolds , Weaving the social fabric: The past, present, and future of optimization problem solving with cultural algorithms, AAAI Fall Symposium: Complex Adaptive Systems, 2010, pp. 2–3. Google Scholar
23. R. G. Reynolds and L. Kinnaird-Heether , Optimization problem solving with auctions in cultural algorithms, Memetic Comput. 5 (2013) 83–94. Crossref, Web of Science, Google Scholar
24. R. G. Reynolds and L. Kinnaird-Heether , Problem solving using social networks in Cultural Algorithms with auctions, IEEE Congress on Evolutionary Computation, 2017. Google Scholar
25. A. Al-Tirawi and R. G. Reynolds , Using common value auction in cultural algorithm to enhance robustness and resilience of social knowledge distribution systems, IEEE Symposium Series on Computational Intelligence, 2018, pp. 1–3. Crossref, Google Scholar
26. R. Morrison and K. D. Jong , A test problem generator for nonstationary environments, Evolutionary Computation, CEC, 1999, pp. 25–31. Google Scholar