Cognitive Control of Self-Evolving Life Forms (SELF) Utilizing Artificial Procedural Memories

  • James A. Crowder
  • John Carbone
  • Shelli Friess


As we have discussed at length in the book, the testing of artificial intelligent systems that are designed to learn over time, based on experience and interaction with their environments is, at best, difficult, and in some cases impossible. This is especially true if the methods and mechanisms to capture the adaptation and changing memories are not built into the overall system design. Here we present one notion of testing and control methodologies for self-adapting artificial intelligent entities, using artificial procedural memories. In general, memories involve the acquisition, categorization, classification, and storage of information. The purpose of memory is to provide the ability to recall information and knowledge as well as events. Through our conceptual recollection of the past we can communicate with the world around us and understand events based on past experiences. The purpose here is to describe a new cognitive architecture for artificial intelligence-controlled devices that incorporates artificial procedural memory creation and recall. This cognitive architecture provides a scalable framework for episodic memory creation as an entity experiences events, and, over time, develops procedural memory “scripts” that allow repetition of tasks it has “learned” to accomplish, while effectively managing its internal knowledge economy. These procedural memories will allow the system to “see into” the brain and adaptation of an artificial intelligent entity by keeping track of changes to the procedural memories, recalling them for analysis to understand how they are changing as the artificial intelligent entity interacts with its environment. The system will utilize a temporal-calculus driven spatial map to store spatio-temporal information, as well as the procedural memories. This provides the system with the cognitive abilities to approach task selection and reason via both experiential and spatial learning.

In order to test and evaluate the viability of artificial memory creation and retrieval, a series of artificially intelligent, cybernetic life forms (cyber insects) were created and tested utilizing a combination of analog and digital neural frameworks allowing procedural memory creation, storage, and retrieval as the methodology for autonomous control of the artificial life form. Presented here are initial design and discussion of artificial analog and digital neural structures along with a discussion of the use of artificial procedural memories, used as autonomous cognitive control of the artificial life form. Lastly, future research needs are proposed for improving the continuous balance of knowledge storage and knowledge necessity relative to prime directives and learned objectives in Self-Evolving Life Forms (SELF).


Analog neurons Self-evolving life form Artificial intelligence Procedural memory 


  1. 1.
    Crowder, J. (2010). Operative Information Software Agents (OISA) for intelligence processing. Proceedings of the 12th annual International Conference on Artificial Intelligence, Las Vegas, NV.Google Scholar
  2. 2.
    Kosko, G. (1986). Fuzzy cognitive maps. International Journal of Man-Machine Studies, 24, 65–75.CrossRefGoogle Scholar
  3. 3.
    Hopfield, J. (1984). Neurons with graded response have collective computational properties like those of two-state neurons. In C. Nicolini (Ed.), Modeling and analysis in biomedicine. New York: World Scientific Publishing.Google Scholar
  4. 4.
    Hutchinson, J., Koch, C., Luo, J., & Mead, C. (1988). Computing motion using analog and binary resistive networks. Computer, 21(3), 52–63.CrossRefGoogle Scholar
  5. 5.
    Kahana, M., Howard, M., & Polyn, S. (2008). Associative retrieval processes in episodic memory. In H. L. Roediger III (Ed.), Cognitive psychology of memory (Vol. 2 of Learning and memory: A comprehensive reference, 4 vols., J. Byrne, Editor). Oxford: Elsevier.Google Scholar
  6. 6.
    Crowder, J., Raskin, V., & Taylor, J. (2012). Autonomous creation and detection of procedural memory scripts. Proceedings of the 13th Annual International Conference on Artificial Intelligence, Las Vegas, NV.Google Scholar
  7. 7.
    Landauer, T., & Dumas, S. (1997). Solution to Plato’s problem: The latent semantic analysis theory of acquisition, induction, and representation of knowledge. Psychological Review, 194, 211–240.CrossRefGoogle Scholar
  8. 8.
    Griffiths, T., & Steyvers, M. (2003). Prediction and semantic association. In K. J. Halmberg & M. Steyvers (Eds.), Advances in neural information processing systems (Vol. 15, pp. 11–18).Google Scholar
  9. 9.
    Carbone, J. (2010). A framework for enhancing transdisciplinary research knowledge. Texas: Tech University.Google Scholar
  10. 10.
    Crowder, J., & Carbone, J. (2011). Recombinant knowledge relativity threads for contextual knowledge storage. Proceedings of the 13th Annual International Conference on Artificial Intelligence, Las Vegas, NV.Google Scholar
  11. 11.
    Crowder, J. (2011). Cognitive architectures for real-time integrated system health management. Proceedings of the 8th Annual Workshop of Structural Health Monitoring, Stanford University, Stanford.Google Scholar
  12. 12.
    Zadeh, L. (2004). A note of web intelligence, world knowledge and fuzzy logic. Data and Knowledge Engineering, 50, 291–304.CrossRefGoogle Scholar
  13. 13.
    Crowder, J., & Carbone, J. (2011). Hybrid neural architectures for the ELYSE cognitive system. Proceedings of the AIAA Infotech@Aerospace 2011 Conference, Garden Grove, CA.Google Scholar
  14. 14.
    Crowder, J., & Carbone, J. (2012). Reasoning frameworks for autonomous systems. Proceedings of the AIAA Infotech@Aerospace 2012 Conference, Garden Grove, CA.Google Scholar
  15. 15.
    Ertas, A., & Tanik, M. (2000). Transdisciplinary engineering education and research model. Transactions of the SDPS, 4(4), 1–11.Google Scholar
  16. 16.
    Crowder, J. (2001). Integrating an expert system into a neural network with genetic programming for process planning. NSA Technical Paper TIT_01_01_013_2001_001.Google Scholar
  17. 17.
    Crowder, J., & Friess, S. (2010). Artificial neural diagnostics and prognostics: Self-soothing in cognitive systems. Proceedings of the 12th Annual International Conference on Artificial Intelligence, Las Vegas, NV.Google Scholar
  18. 18.
    Crowder, J., & Friess, S. (2012). Artificial psychology: The psychology of AI. Proceedings of the 3rd Annual International Multi-Conference on Complexity, Informatics and Cybernetics, Orlando, FL.Google Scholar
  19. 19.
    Raskin, V., Taylor, J. M., & Hemplemann, C. F. (2010). Ausocial engineering. New Security Paradigms Workshop, Concord, MA.Google Scholar
  20. 20.
    Taylor, J. M., & Raskin, V. (2010). Fuzzy ontology for natural language. 29th International Conference of the North American Fuzzy Information Processing Society, Toronto, ON.Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • James A. Crowder
    • 1
  • John Carbone
    • 2
  • Shelli Friess
    • 3
  1. 1.Colorado Engineering Inc.Colorado SpringsUSA
  2. 2.ForcepointAustinUSA
  3. 3.Walden UniversityMinneapolisUSA

Personalised recommendations