Abstract
The traditional approaches—of symbolic artificial intelligence (AI) and of sub-symbolic neural networks—towards artificial cognition have not been very successful. The rule-based symbolic AI approach has proven to be brittle and unable to provide any real intelligence (Mckenna, Artificial intelligence and neural networks: steps toward principled integration, Academic Press, USA, 1994). On the other hand, traditional artificial neural networks have not been able to advance very much beyond pattern recognition and classification. This shortcoming has been credited to the inability of conventional artificial neural networks to handle syntax and symbols. Hybrid approaches that combine symbolic AI and sub-symbolic neural networks have been tried with results that fall short of the ultimate goal. It has been argued that traditional AI programs do not operate with meanings and consequently do not understand anything (Searle, Minds, brains & science, Penguin Books Ltd, London, 1984; Searle, The mystery of consciousness, Granta Books, London, 1997). It seems that in this way some essential ingredient is missing, but there may be a remedy available. Associative information processing principles may enable the utilization of meaning and the combined sub-symbolic/symbolic operation of neural networks.
Similar content being viewed by others
References
Hebb DO. The organization of behavior. New York: Wiley; 1949.
Jain AK, Mao J, Mohiuddin KM. Artificial neural networks: a tutorial. Computer. 1996;29(3):31–44.
Mckenna TM. The role of interdisciplinary research involving neuroscience in the development of intelligent systems. In: Honavar V, Uhr L, editors. Artificial intelligence and neural networks: steps toward principled integration. USA: Academic Press; 1994. p. 75–92.
Searle JR. Minds, brains & science. London, England: Penguin Books Ltd; 1984.
Searle JR. The mystery of consciousness. London: Granta Books; 1997.
McGarry K, Wermter S, MacIntyre J. Hybrid neural systems: from single coupling to fully integrated neural networks. Neural Comput Surv. 1999;2:62–93.
Smolensky P, Legendre G, Miyata Y. Integrating connectionist and symbolic computation for the theory of language. In: Honavar V, Uhr L, editors. Artificial intelligence and neural networks: steps toward principled integration. USA: Academic Press; 1994. p. 509–30.
Kelley TD. Symbolic and sub-symbolic representations in computational models of human cognition. Theory Psychol. 2003;13(6):847–60.
Haikonen PO. An artificial cognitive neural system based on a novel neuron structure and a reentrant modular architecture with implications to machine consciousness. Dissertation for the degree of Doctor of Technology, Helsinki University of Technology, Applied Electronics Laboratory, Series B: Research Reports B4; 1999.
Haikonen PO. Robot brains, circuits and systems for conscious machines. UK: Wiley; 2007.
Haikonen PO. Towards streams of consciousness; implementing inner speech. In: The proceedings of AISB’06: adaptation in artificial and biological systems, vol 1. Bristol, UK: University of Bristol; 2006. p. 144–9.
Gruber TR. A translation approach to portable ontology specifications. Knowl Acquis. 1993;5(2):199–220 (http://tomgruber.org/writing/ontolingua-kaj-1993.htm).
Amigoni F, Neri MA. An application of ontology technologies to robotic agents. In: Proceedings of the 2005 IEEE/WIC/ACM international conference on intelligent agent technology. Compiegne, France, 19–22 September. IEEE Computer Society; 2005. p. 751–4.
Chella A, Cossentino M, Pirrone R, Ruisi A. Modeling ontologies for robotic environments. In: Proceedings of SEKE’2002, fourteenth international conference on software engineering and knowledge engineering. Ischia, Italy; 2002. p. 77–82.
Sato E, Hoshi S, Yamaguchi T. Humane robot system using ontological network. In: Proceedings of 2004 IEEE/RSJ international conference on intelligent robots and systems. 28 September–2 October. Sendai, Japan; 2004. p. 4038–43.
Costa PCG, Laskey KB, AlGhamdi G. Bayesian ontologies in AI systems. Paper presented at the fourth bayesian modelling applications workshop, held at the twenty-second conference on uncertainty in artificial intelligence (UAI 2006). 13 July. Cambridge, MA, USA; 2006.
Clancey WJ. The frame of reference problem in cognitive modeling. In: Proceedings of 11th annual conference of the cognitive science society. Ann Arbor: Lawrence Erlbaum Associates; 1989. p. 107–14.
Hinton GE, McClelland JL, Rumelhart DE. Distributed representations. In: Boden MA, editor. The philosophy of artificial intelligence. New York: Oxford University Press; 1990. p. 248–80.
Anderson JA. An introduction to neural networks. USA: MIT Press; 1995.
Pavlov IP. Conditional reflexes. New York: Dover Publications; 1927/1960.
Grossberg S. Pavlovian pattern learning by nonlinear neural networks. Proc Natl Acad Sci USA. 1971;4:828–31.
Vogel EH, Castro ME, Saavedra MA. Quantitative models of Pavlovian conditioning. Brain Res Bull. 2004;63:173–202.
Anderson JA. A simple neural network generating an interactive memory. Math Biosci. 1972;14:197–220.
Haque AL, Cheung JY. Preprocessing of the input vectors for the linear associator neural networks. In: The proceedings of IEEE international conference on neural networks, vol. 2; 1994. p. 930–3.
Hopfield JJ. Neural networks and physical systems with emergent collective computational properties. Proc Natl Acad Sci USA. 1982;79:2554–8.
Eliasmith C. Attractor network. Scholarpedia. 2007;2(10):1380.
Dodd W, Gutierrez R. The role of episodic memory and emotion in a cognitive robot. In: Proceedings of the IEEE international workshop on robot and human interactive communication (RO-MAN), Nashville, Tennessee, 13–15 August 2005; p. 692–7.
Chella A. Towards robot conscious perception. In: Chella A, Manzotti R, editors. Artificial consciousness. UK: Imprint Academic; 2007.
Chella A. Perception loop and machine consciousness. APA Newsletter on Philosophy and Computers. 2008;2:7–9.
Haikonen PO. The cognitive approach to conscious machines. UK: Imprint Academic; 2003.
Hesslow G, Jirenhed DA. The inner world of a simple robot. J Conscious Stud. 2007;14:85–96.
Miller GA. The magical number seven plus or minus two: some limits on our capacity for processing information. Psychol Rev. 1956;63:81–97.
Zwaan RA, Radvansky GA. Situation models in language comprehension and memory. Psychol Bull. 1998;2:162–85.
Acknowledgement
I wish to thank Mr. Dylan Drummond for kindly perusing the first draft of this paper and for valuable comments.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Haikonen, P.O.A. The Role of Associative Processing in Cognitive Computing. Cogn Comput 1, 42–49 (2009). https://doi.org/10.1007/s12559-009-9006-y
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-009-9006-y