Advertisement

Universal Learning Machine – Principle, Method, and Engineering Model Contributions to ICIS 2018

  • Chuyu Xiong
Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 539)

Abstract

Universal learning machine is a computing system that can automatically learn any computational task with sufficient data, and no need for manual presetting and intervention. Universal learning machine and universal learning theory are very important research topic. Many disciplines (AI, AGI, machine epistemology, neuroscience, computational theory, mathematics, etc.) cross here. In this article, we discuss the principles, methods, and engineering models of universal learning machine. X-form is the central concept and tool, which is introduced by examining objective and subjective patterns in details. We also discuss conceiving space and governing space, data sufficiency, learning strategies and methods, and engineering model.

Keywords

Universal learning machine Subjective pattern X-form Conceiving space Governing space Primary consciousness Learning dynamics Data sufficiency Squeeze to higher abstraction Embed to parameter space 

References

  1. 1.
    Xiong, C.: Discussion on mechanical learning and learning machine. arxiv.org (2016). http://arxiv.org/pdf/1602.00198.pdf
  2. 2.
    Xiong, C.: Descriptions of objectives and processes of mechanical learning. arxiv.org (2017). http://arxiv.org/abs/1706.00066.pdf
  3. 3.
    Xiong, C.: What really is deep learning doing. arxiv.org (2017). http://arxiv.org/abs/1711.03577.pdf
  4. 4.
    Xiong, C.: Chinese patent application. Application # 201710298481.2. (in Chinese)Google Scholar
  5. 5.
    Xiong, C.: Principle, method and engineering model of universal learning machine. Researchage.net (2018). (in Chinese). https://www.researchgate.net/publication/323915356_jisuanjijinxingtongyongxuexideyuanlifangfahegongchengmoxing
  6. 6.
    Domingos, P.: The Master Algorithm, Talks at Google. https://plus.google.com/117039636053462680924/posts/RxnFUqbbFRc
  7. 7.
    Valiant, L.: A theory of the learnable. Commun. ACM 27 (1984). http://web.mit.edu/6.435/www/Valiant84.pdfzbMATHCrossRefGoogle Scholar
  8. 8.
    Wang, P.: A Logical Model of Intelligence: An Introduction to NARS. https://sites.google.com/site/narswang/home/nars-introduction?pli=1
  9. 9.
    Zhong, Y.: Mechanism-based artificial intelligence theory. CAAI Trans. Intell. Syst. 13(1), 2–18 (2018). (in Chinese)Google Scholar
  10. 10.
    He, H.: Universal logic theory: logical foundation of mechanism-based artificial intelligence theory. CAAI Trans. Intell. Syst. 13(1), 19–36 (2018). (in Chinese)Google Scholar
  11. 11.
    Wang, P.: Factor space-mathematical basis of mechanism based artificial intelligence theory. CAAI Trans. Intell. Syst. 13(1), 37–54 (2018). (in Chinese)Google Scholar

Copyright information

© IFIP International Federation for Information Processing 2018

Authors and Affiliations

  • Chuyu Xiong
    • 1
  1. 1.New YorkUSA

Personalised recommendations