Abstract
Construction of integrated neural-symbolic systems is an actual and challenging task. Such hybrid systems combine advantages of connectionist and symbolic approaches. In particular, neural-symbolic systems are characterized by robust learning and distributed neural computations. At the same time, they can be interpreted, described and analyzed in logical terms. Especially high interpretability is important for Decision Support Systems that operate with symbolic structures describing the problem situation, stakeholders, assessment criteria and where the reasoning process should be transparent for the Decision Maker. Such requirements bring the task of designing integrated neural-symbolic Decision Support Systems to the higher level of complexity. This paper examines underlying algorithms of a specific part of Decision Support Systems that is aggregation of experts’ assessments to make the choice among alternative solutions of the given problem. Such fuzzy and uncertain assessments are often represented as 2-tuple model or its derivatives and algorithms that aggregate them are often called operator. We demonstrate that the simple aggregation operator can be expressed in a fully connectionist form with the help of Neural Turing Machine architecture. This result sheds new light on the way principles of symbolic computation can be implemented by connectionist mechanisms.
The reported study was funded by RFBR, project number 19–37-90058.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Matzkevich, I., Abramson, B.: Decision analytic networks in artificial intelligence. Manage. Sci. 41(1), 1–22 (1995)
Silverman, B.G.: Unifying expert systems and the decision sciences. Oper. Res. 42(3), 393–413 (1994)
Kelley, T.D.: Symbolic and sub-symbolic representations in computational models of human cognition: what can be learned from biology? Theory Psychol. 13(6), 847–860 (2003)
Pylyshyn, Z.W.: Computing in Cognitive Science. University of Western Ontario, Centre for Cognitive Science, London (1988)
Turek, M.: Explainable Artificial Intelligence (XAI) (2018). https://www.darpa.mil/program/explainable- artificial- intelligence. Accessed 27 June 2020
Smolensky, P., Legendre, G.: The Harmonic Mind: From Neural Computation to Optimality-Theoretic Grammar (Cognitive Architecture), vol. 1. MIT press, Cambridge (2006)
Plate, T.A.: Holographic reduced representations. IEEE Trans. Neural Netw. 6(3), 623–641 (1995)
Kanerva, P.: Hyperdimensional computing: an introduction to computing in distributed representation with high-dimensional random vectors. Cogn. Comput. 1(2), 139–159 (2009)
Schlegel, K., Neubert, P., Protzel, P.: A comparison of vector symbolic architectures. arXiv preprint arXiv:2001.11797 (2020)
Harnad, S.: The symbol grounding problem. Physica D 42(1–3), 335–346 (1990)
Anderson, J.R., Lebiere, C.J.: The Atomic Components of Thought. Psychology Press, Hove (2014)
Sun, R., Peterson, T.: A hybrid agent architecture for reactive sequential decision making. Connectionist symbolic integration: From unified to hybrid approaches, pp.113–138 (1997)
Avery, E., Kelley, T.D., Davani, D.: May. Using cognitive architectures to improve robot control: Integrating production systems, semantic networks, and sub-symbolic processing. In: 15th Annual Conference on Behavioral Representation in Modeling and Simulation (BRIMS) (2006)
Kelley, T., Avery, E., Long, L., Dimperio, E.: A hybrid symbolic and sub-symbolic intelligent system for mobile robots. In: AIAA Infotech@ Aerospace Conference and AIAA Unmanned... Unlimited Conference, p. 1976 (2009)
Parvar, J., Lowe, D., Emsley, M., Duff, R.: Neural networks as a decision support system for the decision to bid process. In: Proceedings ARCOM Conference, vol. 1, pp. 209–217 (2000)
Delen, D., Sharda, R.: Artificial neural networks in decision support systems. In: Burstein, F., Holsapple, C.W. (eds.) Handbook on Decision Support Systems 1, pp. 557–580. Springer, Heidelberg (2008). https://doi.org/10.1007/978-3-540-48713-5_26
Power, D.J., Sharda, R.: Model-driven decision support systems: concepts and research directions. Decis. Support Syst. 43(3), 1044–1061 (2007)
Power, D.J.: Decision Support Systems: Concepts and Resources for Managers. Greenwood Publishing Group, Westport (2002)
Golmohammadi, D.: Neural network application for fuzzy multi-criteria decision making problems. Int. J. Prod. Econ. 131(2), 490–504 (2011)
Yoon, K., Hwang, C.L.: TOPSIS (Technique for Order Preference by Similarity to Ideal Solution)–A Multiple Attribute Decision Making, W: Multiple Attribute Decision Making–Methods and Applications, A State-of-the-at Survey. Springer, Heidelberg (1981).https://doi.org/10.1007/978-3-642-48318-9
Figueira, J.R., Mousseau, V., Roy, B.: ELECTRE methods. In: Greco, S., Ehrgott, M., Figueira, J.R. (eds.) Multiple criteria decision analysis. ISORMS, vol. 233, pp. 155–185. Springer, New York (2016). https://doi.org/10.1007/978-1-4939-3094-4_5
Demidovskij, A.V., Babkin, E.A.: Developing a distributed linguistic decision making system. Bus. Inf. 13(1), 18–32 (2019)
Zhang, H., Wu, Y., Gao, J., Xu, C.: A method for multi-criteria group decision making with 2-tuple linguistic information based on cloud model. Information 8(2), 54 (2017)
Herrera, F., Martínez, L.: A 2-tuple fuzzy linguistic representation model for computing with words. IEEE Trans. Fuzzy Syst. 8(6), 746–752 (2000)
Wei, C., Liao, H.: A multigranularity linguistic group decision-making method based on hesitant 2-tuple sets. Int. J. Intell. Syst. 31(6), 612–634 (2016)
Wei, G., Lu, M., Alsaadi, F.E., Hayat, T., Alsaedi, A.: Pythagorean 2-tuple linguistic aggregation operators in multiple attribute decision making. J. Intell. Fuzzy Syst. 33(2), 1129–1142 (2017)
Rodriguez, R.M., Martinez, L., Herrera, F.: Hesitant fuzzy linguistic term sets for decision making. IEEE Trans. Fuzzy Syst. 20(1), 109–119 (2011)
Liu, P., Chen, S.M.: Multiattribute group decision making based on intuitionistic 2-tuple linguistic information. Inf. Sci. 430, 599–619 (2018)
Wei, G., Alsaadi, F.E., Hayat, T., Alsaedi, A.: Picture 2-tuple linguistic aggregation operators in multiple attribute decision making. Soft. Comput. 22(3), 989–1002 (2016). https://doi.org/10.1007/s00500-016-2403-8
Wang, J.H., Hao, J.: A new version of 2-tuple fuzzy linguistic representation model for computing with words. IEEE Trans. Fuzzy Syst. 14(3), 435–445 (2006)
Demidovskij, A., Babkin, E.: Designing a neural network primitive for conditional structural transformations. In: Kuznetsov, S.O., Panov, A.I., Yakovlev, K.S. (eds.) Artificial Intelligence: 18th Russian Conference, RCAI 2020, Moscow, Russia, October 10–16, 2020, Proceedings, pp. 117–133. Springer International Publishing, Cham (2020). https://doi.org/10.1007/978-3-030-59535-7_9
Demidovskij, A., Babkin, E.: Designing arithmetic neural primitive for sub-symbolic aggregation of linguistic assessments. In: Journal of Physics: Conference Series, vol. 1680, No. 1. IOP Publishing, December (2020)
Graves, A., Wayne, G., Danihelka, I.: Neural turing machines. arXiv preprint arXiv:1410.5401 (2014)
Graves, A., et al.: Hybrid computing using a neural network with dynamic external memory. Nature 538(7626), 471–476 (2016)
Zaremba, W., Sutskever, I.: Reinforcement learning neural turing machines-revised. arXiv preprint arXiv:1505.00521 (2015)
Chen, X., et al.: Sequential recommendation with user memory networks. In Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining, pp. 108–116, February 2018
Grefenstette, E., Hermann, K.M., Suleyman, M., Blunsom, P.: Learning to transduce with unbounded memory. arXiv preprint arXiv:1506.02516 (2015)
Collier, M., Beel, J.: Implementing neural turing machines. In: Kůrková, V., Manolopoulos, Y., Hammer, B., Iliadis, L., Maglogiannis, I. (eds.) ICANN 2018. LNCS, vol. 11141, pp. 94–104. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-01424-7_10
Castellini, J.: Learning numeracy: binary arithmetic with neural turing machines. arXiv preprint arXiv:1904.02478 (2019)
Demidovskij, A.: Neural turing machine: open-source project. https://github.com/demid5111/NeuralTuringMachine Accessed 7 Apr 2021
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Demidovskij, A., Babkin, E. (2022). Neural Multigranular 2-tuple Average Operator in Neural-Symbolic Decision Support Systems. In: Kovalev, S., Tarassov, V., Snasel, V., Sukhanov, A. (eds) Proceedings of the Fifth International Scientific Conference “Intelligent Information Technologies for Industry” (IITI’21). IITI 2021. Lecture Notes in Networks and Systems, vol 330. Springer, Cham. https://doi.org/10.1007/978-3-030-87178-9_35
Download citation
DOI: https://doi.org/10.1007/978-3-030-87178-9_35
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-87177-2
Online ISBN: 978-3-030-87178-9
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)