Abstract
This paper compares the various conceptions of “real-time” in the context of AI, as different ways of taking the processing time into consideration when problems are solved. An architecture of real-time reasoning and learning is introduced, which is one aspect of the AGI system NARS. The basic idea is to form problem-solving processes flexibly and dynamically at run time by using inference rules as building blocks and incrementally self-organizing the system’s beliefs and skills, under the restriction of time requirements of the tasks. NARS is designed under the Assumption of Insufficient Knowledge and Resources, which leads to an inherent ability to deal with varying situations in a timely manner.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
References
Cormen, T.H., Leiserson, C.E., Rivest, R.L., Stein, C.: Introduction to Algorithms, 3rd edn. MIT Press, Cambridge (2009)
Dean, T., Boddy, M.: An analysis of time-dependent planning. In: Proceedings of AAAI-1988, pp. 49–54 (1988)
Garvey, A., Lesser, V.: Design-to-time real-time scheduling. IEEE Trans. Syst. Man Cybern. Special Issue Plan. Schedul. Control 23(6), 1491–1502 (1993)
Hammer, P., Lofthouse, T.: Goal-directed procedure learning. In: Proceedings of the Eleventh Conference on Artificial General Intelligence, pp. 77–86 (2018)
Hammer, P., Lofthouse, T., Wang, P.: The OpenNARS implementation of the Non-Axiomatic reasoning system. In: Proceedings of the Ninth Conference on Artificial General Intelligence, pp. 160–170 (2016)
Hopcroft, J.E., Motwani, R., Ullman, J.D.: Introduction to Automata Theory, Languages, and Computation, 3rd edn. Addison-Wesley, Boston (2007)
Horvitz, E.J.: Reasoning about beliefs and actions under computational resource constraints. In: Kanal, L.N., Levitt, T.S., Lemmer, J.F. (eds.) Uncertainty in Artificial Intelligence 3, pp. 301–324. North-Holland, Amsterdam (1989)
Ikle, M., Pitt, J., Sellmann, G., Goertzel, B.: Economic attention networks: associative memory and resource allocation for general intelligence. In: Proceedings of the Second Conference on Artificial General Intelligence, pp. 73–78 (2009)
Korf, R.E.: Real-time heuristic search. Artif. Intell. 42(2–3), 189–211 (1990)
Laffey, T.J., Cox, P.A., Schmidt, J.L., Kao, S.M., Read, J.Y.: Real-time knowledge-based systems. AI Magazine 9, 27–45 (1988)
Musliner, D.J., Hendler, J.A., Agrawala, A.K., Durfee, E.H., Strosnider, J.K., Paul, C.J.: The challenges of real-time AI. Computer 28(1), 58–66 (1995)
Nivel, E., Thórisson, K.R., Steunebrink, B., Schmidhuber, J.: Anytime bounded rationality. In: Proceedings of the Eighth Conference on Artificial General Intelligence. pp. 121–130. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-21365-1_13
Russell, S., Wefald, E.H.: Principles of metareasoning. Artif. Intell. 49, 361–395 (1991)
Silberschatz, A., Galvin, P.B., Gagne, G.: Operating System Concepts, 9th edn. Wiley, Hoboken (2012)
Stankovic, J.A.: Real-time computing systems: the next generation. Technical report 88–06, University of Massachusetts, Amherst (1988)
Wang, P.: Problem solving with insufficient resources. Int. J. Uncertainty, Fuzziness Knowl.-based Syst. 12(5), 673–700 (2004)
Wang, P.: Rigid Flexibility: The Logic of Intelligence. Springer, Dordrecht (2006). https://doi.org/10.1007/1-4020-5045-3
Wang, P.: Case-by-case problem solving. In: Proceedings of the Second Conference on Artificial General Intelligence, pp. 180–185 (2009)
Wang, P.: Solving a problem with or without a program. J. Artif. General Intell. 3(3), 43–73 (2012)
Wang, P.: Non-Axiomatic Logic: A Model of Intelligent Reasoning. World Scientific, Singapore (2013)
Wang, P.: On defining artificial intelligence. J. Artif. General Intell. 10(2), 1–37 (2019)
Zilberstein, S.: Operational rationality through compilation of anytime algorithms. AI Magazine 16(2), 79–80 (1995)
Acknowledgement
This work is partially supported by a gift from the Cisco University Research Program Fund, a corporate advised fund of Silicon Valley Community Foundation.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, P., Hammer, P., Wang, H. (2020). An Architecture for Real-Time Reasoning and Learning. In: Goertzel, B., Panov, A., Potapov, A., Yampolskiy, R. (eds) Artificial General Intelligence. AGI 2020. Lecture Notes in Computer Science(), vol 12177. Springer, Cham. https://doi.org/10.1007/978-3-030-52152-3_37
Download citation
DOI: https://doi.org/10.1007/978-3-030-52152-3_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-52151-6
Online ISBN: 978-3-030-52152-3
eBook Packages: Computer ScienceComputer Science (R0)