Self-organizing cognitive model synthesis with deep learning support

  • Authors

    • A Raikov
    • A Ermakov
    • A Merkulov
    2018-05-16
    https://doi.org/10.14419/ijet.v7i2.28.12904
  • automated synthesis, big data, cognitive modelling, deep learning, convergent methodology, monoidal category, tourist planning.

  • Abstract

    Cognitive models are created by experts and the process takes a lot of time. Furthermore, the result of expert work needs to be verified especially in cases when experts do not have complete information and cannot understand the problem situation quickly. As was previously shown cognitive models’ factors and their mutual relationships could be verified with applying Big Data analysis technology. This paper addresses the issue of automated cognitive models synthesis on the base of author’s convergent methodology, artificial intelligence and deep learning technology.

     

  • References

    1. [1] Raikov AN, Avdeeva Z, & Ermakov A. (2016), “Big Data refining on the base of cognitive modelingâ€, Proceedings of the 1st IFAC Conference on Cyber-Physical&Human-Systems, Florianopolis, Brazil, 147-152

      [2] Raikov AN (2008), “Convergent cognitype for speeding-up the strategic conversationâ€, Proceedings of the 17th World Congress of the International Federation of Automatic Control (IFAC), Seoul, Korea, 8103-8108

      [3] Preparing for the future of artificial intelligence (2016),. Executive Office of the President National Science and Technology Council Committee on Technology, USA, 58 p

      [4] Adrian B, Marcia K & Judith H (2015), Cognitive Computing and Big Data Analytics, Wiley, 291 p

      [5] Munéo K (2016), Memory and action selection in human-machine interaction. John Wiley & Sons, Incorporated, 163 р

      [6] Atmanspacher H (2017), “Quantum approaches to brain and mind. An overview with representative examplesâ€, The Blackwell Companion to Consciousness, Ed. Susan Schneider and Max Velmans, John Wiley & Sons Ltd, pp. 298-313, doi: 10.1002/9781119132363.ch21

      [7] Huelga SH & Plenio MB (2013), “Vibrations, quanta, and biologyâ€, Contemporary Physics 54, pp. 181–207, doi.org/10.1080/00405000.2013.829687

      [8] Jung CG & Pauli W (1955), The interpretation of nature and the psyche, Published by Routledge & Kegan Paul, The Topsham Bookshop, EXETER, DEVON, United Kingdom

      [9] Ellis GFR, Noble D, O’Connor T (eds.) (2012), “Top Down Causation: An Integrating Theme Within and Across the Sciences?â€, Interface Focus., Feb 6, 2(1): 1–3. doi: 10.1098/rsfs.2011.0110

      [10] DeFlitch CJ, Bastian ND, Munoz D A, Kang H, Nembhard HB & Griffin PM (2016), “Healthcare Systems Engineeringâ€, John Wiley & Sons, Incorporated, 382 p

      [11] Kartsaklis D, Ramgoolam S & Sadrzadeh M (2017), Linguistic Matrix Theory. arXiv:1703.10252v1 (cs.CL), 28 Mar

      [12] Raikov A (2015), Convergent networked decision-making using group insights, Complex & Intelligent Systems. December, V. 1, Issue 1, pp. 57-68

      [13] Marsden D (2017), “Ambiguity and Incomplete Information in Categorical Models of Languageâ€, University of Oxford, Duncan R and Heunen C (Eds.): Quantum Physics and Logic (QPL), 2016 EPTCS 236, pp. 95–107

      [14] Selinger P (2007), “Dagger Compact Closed Categories and Completely Positive Maps: (Extended Abstract)â€, Electronic Notes Theoretical Computer Science 170, pp. 139–163

      [15] Goodfellow I, Bengio Y & Courville A (2016), Deep Learning. The MIT Press, 800 p

      [16] Data Feeds Power The Top Media Monitoring and Big Data Analytics Players, https://webhose.io/ (last accessed 20.04.2018)

      [17] Le Q & Mikolov T (2014), “Distributed Representations of Sentences and Documentsâ€, Proceedings of the 31st International Conference on Machine Learning, Beijing, China, JMLR: W&CP volume 32 (https://cs.stanford.edu/~quocle/paragraph_vector.pdf)

      [18] Mikolov T, Sutskever I, Chen K, Corrado G & Dean J (2013), “Distributed Represetations of Words and Phrases and their Compositionalityâ€, NIPS'13 Proceedings of the 26th International Conference on Neural Information Processing Systems – V. 2, pp 3111-3119, Lake Tahoe, Nevada, USA — December

      [19] Smirnova E & Vasile F (2017), “Contextual Sequence Modeling for Recommendation with Recurrent Neural Networksâ€, Proceedings of ACM Recommender Systems conference, Como, Italy, 27th-31st August 2017 (RecSys ’17), 8 pages. doi: 10.475/123_4

  • Downloads

  • How to Cite

    Raikov, A., Ermakov, A., & Merkulov, A. (2018). Self-organizing cognitive model synthesis with deep learning support. International Journal of Engineering & Technology, 7(2.28), 168-172. https://doi.org/10.14419/ijet.v7i2.28.12904

    Received date: 2018-05-16

    Accepted date: 2018-05-16

    Published date: 2018-05-16