Abstract
The concept of understanding is commonly used in everyday communications, and seems to lie at the heart of human intelligence. However, no concrete theory of understanding has been fielded as of yet in artificial intelligence (AI), and references on this subject are far from abundant in the research literature. We contend that the ability of an artificial system to autonomously deepen its understanding of phenomena in its surroundings must be part of any system design targeting general intelligence. We present a theory of pragmatic understanding, discuss its implications for architectural design and analyze the behavior of an intelligent agent implementing the theory. Our agent learns to understand how to perform multimodal dialogue with humans through observation, becoming capable of constructing sentences with complex grammar, generating proper question-answer patterns, correctly resolving and generating anaphora with coordinated deictic gestures, producing efficient turntaking, and following the structure of interviews, without any information on this being provided up front.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Exceptions do exist of course (cf. [1]), but not in the obvious areas such as language-, image- and scene-understanding, where the word makes a mere superfluous appearance.
- 2.
By “elements” and “sub-parts” we mean any sub-division of \(\varPhi \), including sub-structures, component processes, whole-part relations, causal relations, etc.
- 3.
Producing plans, while not being as specific as requiring intimate familiarity with some I/O devices to every \(\varPhi \), requires nevertheless knowledge of some language for producing said plans, but it is somewhat more general and thus probably a better choice.
- 4.
Feynman, notorious for his capacity to understand even the most complicated phenomena in his field, left a note on his blackboard when he died: “What I cannot create, I do not understand.” (http://archives-dc.library.caltech.edu/islandora/object/ct1:483 - accessed Apr 2, 2016).
- 5.
A datum \(d_t\) can be an event, an utterance, the perception of a particular object, a particular deduction or set of deductions, etc. occurring at time t – in short, anything that can be perceived by the agent’s sensors and represented by its mind.
- 6.
Unless otherwise specified the term “goal” may be read to mean “all active goals”, as typically this is a set of goals; even if a single identifiable top-level goal can be found, there will always be (obvious and non-obvious) sub-goals that must be taken into account. We thus use “goal” and “goals” indiscriminately.
- 7.
Another determinant of the quality of predictions is the observability of variables and the accuracy of reading their values. For any triplet \(\{A,G,S\}\), to produce predictions requires fixing the values of numerous variables \(v \in V \subset S\) whose values may not be immediately accessible (and thus guessed or retrieved from the agent’s prior experience), or whose values may not be perfectly observable (cf. “Does that display show 880 or 830?”).
References
Baum, E.: Project to build programs that understand. In: Proceedings of the Second Conference on Artificial General Intelligence, pp. 1–6 (2009)
Chalmers, D.J.: Subsymbolic computation and the chinese room. In: Dinsmore, J. (ed.) The Symbolic and Connectionist Paradigms: Closing the Gap. Lawrence Erlbaum, Hillsdale (1992)
Fisher, J.A.: The wrong stuff: chinese rooms and the nature of understanding. Philos. Inves. 11(4), 279–299 (1988)
von Forrester, H.: Understanding Understanding: Essays on Cybernetics and Cognition. Springer, New York (2003)
Franklin, R.L.: On understanding. Philos. Phenomenological Res. 43(3), 307–328 (1983)
de Gelder, B.: I know what you mean, but if only i understood you\(\ldots \) In: Parret, H., Bouveresse, J. (eds.) Meaning and Understanding, pp. 44–61. de Gruyter, Berlin (1981)
Grimm, S.R.: The value of understanding. Philos. Compass 7(2), 279–299 (1988)
Grimm, S.R.: Understanding as knowledge of causes. In: Fairweather, A. (ed.) Virtue Epistemology Naturalized, pp. 329–345. Springer, Switzerland (2014)
Herman Parret, J.B.: Meaning and Understanding. Walter de Gruyer, New York (1981)
Kvanvig, J.: The Value of Knowledge and the Pursuit of Understanding. Cambridge University Press, Cambridge (2003)
Nivel, E., Thórisson, K.R., et al.: Bounded recursive self-improvement. RUTR 13006 (2012)
Nivel, E., Thórisson, K.R., et al.: Autonomous acquisition of natural language. In: IADIS International Conference on Intelligent Systems & Agents, pp. 58–66 (2014)
Nivel, E., Thórisson, K.R., Steunebrink, B.R., Dindo, H., Pezzulo, G., Rodríguez, M., Hernández, C., Ognibene, D., Schmidhuber, J., Sanz, R., Helgason, H.P., Chella, A.: Bounded seed-AGI. In: Goertzel, B., Orseau, L., Snaider, J. (eds.) AGI 2014. LNCS, vol. 8598, pp. 85–96. Springer, Heidelberg (2014)
Pattee, H.H.: Evolving self-reference: matter, symbols, and semantic closure. In: Laws, Language and Life: Howard Pattee’s Classic Papers on the Physics of Symbols with Contemporary Commentary, pp. 211–226 (2012)
Potter, V.G.: On Understanding Understanding: A Philosophy of Knowledge. Fordham University Press, New York (1994)
Kurzweil, R., Richards, J.W., Gilder, G.: Are We Spiritual Machines? Ray Kurzweil vs. the Critics of Strong AI. Discovery Institute Press, Seattle (2002)
Conant, R.C., Ross Ashby, W.: Every good regulator of a system must be a model of that system. Int. J Syst. Sci. 1(2), 89–97 (1970)
Sloman, A.: What enables a machine to understand? In: Proceedings 9th International Joint Conference on AI, pp. 995–1001 (1985)
Steunebrink, B., Thórisson, K.R., Schmidhuber, J.: Growing recursive self-improvers. In: Proceedings of the 9th Conference on Artificial General Intelligence (2016)
Thórisson, K.R.: A new constructivist AI: from manual construction to self-constructive systems. In: Wang, P., Goertzel, B. (eds.) Theoretical Foundations of Artificial General Intelligence, pp. 145–171. Atlantis Press, Amsterdam (2012)
Acknowledgments
We would like to thank our HUMANOBS collaborators’ valuable contributions to the AERA system. This work was sponsored in part by the School of Computer Science at Reykjavik University, by a European Project HUMANOBS (FP7 STREP #231453), by a Centers of Excellence Grant from the Science & Technology Policy Council of Iceland, and by a grant from the Future of Life Institute.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2016 Springer International Publishing Switzerland
About this paper
Cite this paper
Thórisson, K.R., Kremelberg, D., Steunebrink, B.R., Nivel, E. (2016). About Understanding. In: Steunebrink, B., Wang, P., Goertzel, B. (eds) Artificial General Intelligence. AGI 2016. Lecture Notes in Computer Science(), vol 9782. Springer, Cham. https://doi.org/10.1007/978-3-319-41649-6_11
Download citation
DOI: https://doi.org/10.1007/978-3-319-41649-6_11
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-41648-9
Online ISBN: 978-3-319-41649-6
eBook Packages: Computer ScienceComputer Science (R0)