Research Article

Is the Algorithm of Artificial Neural Network a Deduction or Induction? Discussion between Natural Sciences, Mathematics and Philosophy

Jyh-Woei Lin
Nanjing University of Information Science & Technology, China
* Corresponding author
DOI icon 10.24018/compute.2021.1.4.29

Read Counter
629

Downloads
394

Citations

Share

Article Sidebar

Submitted 2021-09-08
Published 2021-09-30

Read counter = 629 times

Table of Contents

Article Main Content

The algorithm of artificial neural network (ANN) has been defined as a supervised learning and heuristic algorithms. In training an ANN model, big data is necessary to use as training data to obtain perfectly accurate predicted data. However, big data really have no clear definition. Therefore, adding new training data to re-train an ANN model, by which can improve the predicted accuracy. This action of re-training this ANN model with added new training data is repeated to approach the laws of physics that is accessed to the principle of induction e.g., empirical formulas. However, accessing the principle of induction is limited. If the deduction is found using an ANN model, then approach of this ANN model with added new training data is also performed repeatedly to access the principle of deduction e.g., theory formulas. However, accessing the principle of deduction is also limited. It means the law cannot be easily deduced for an ANN model. Therefore, the algorithm of an ANN is not the canonical classical methods. On the other hand, the algorithm of an ANN does not belong to mathematical induction and deduction.

Keywords: Artificial neural network (ANN), induction, empirical formulas, deduction, theory formulas, canonical classical methods

References

  1. D. E. Rumelhart, G. E. Hinton and R. J. Williams, “Learning representations by back-propagating errors,” Nature 323, 533–536,1986. doi: 10.1038/323533a0.
     Google Scholar
  2. I. Hussain and D. M. Thounaojam, “SpiFoG: an efficient supervised learning algorithm for the network of spiking neurons,” Scientific Reports 10, 13122,2020. doi: 10.1038/s41598-020-70136-5.
     Google Scholar
  3. M. Hilbert and P. López, “The World’s Technological Capacity to Store, Communicate, and Compute Information,” Science 332 (6025), 60-65, 2011. doi: 10.1126/science.1200970.
     Google Scholar
  4. J. W. Lin, “An empirical correlation between the occurrence of earthquakes and typhoons in Taiwan: a statistical multivariate approach,” Natural Hazards 65, 605–634, 2013. doi: 10.1007/s11069-012-0382-3.
     Google Scholar
  5. S. Yaghmaei-Sabegh and R. Motallebzade, “An effective procedure for seismic hazard analysis including nonlinear soil response,” Natural Hazards 64(2), 1731-1752, 2012. doi: 10.1007/s11069-012-0332-0.
     Google Scholar
  6. J. W. Lin and J. S. Chiou, “Detecting Total Electron Content Precursors Before Earthquakes by Examining Total Electron Content Images Based on Butterworth Filter in Convolutional Neural Networks,” IEEE Access 8, 110478 – 110494, 2020. doi: 10.1109/ACCESS.2020.3001337.
     Google Scholar
  7. N. R. Jennings, “On agent-based software engineering,” Artificial Intelligence 117 (2), 277-296, 2000. doi: 10.1016/S0004-3702(99)00107-1.
     Google Scholar
  8. J. Stoer and R. Bulirsch, “Introduction to Numerical Analysis,” 12, 746, Springer Science & Business Media, 2013.
     Google Scholar
  9. Y. Wu, G. Peng, H. Wang and H. Zhang, “A Heuristic Algorithm for Optimal Service Composition in Complex Manufacturing Networks,” Complexity 7819523, 2019. doi:10.1155/2019/7819523.
     Google Scholar
  10. J. Kennedy, “Particle Swarm Optimization,” Encyclopedia of Machine Learning. Springer, 760-766, 2010.
     Google Scholar
  11. L. M. Almeida and T. Ludermir, “An improved method for automatically searching near-optimal artificial Neural Networks,” IEEE World Congress on Computational Intelligence 2235-2242, 2008. doi: 10.1109/IJCNN.2008.4634107.
     Google Scholar
  12. X. S. Yang, “Nature-inspired Metaheuristic Algorithms,” Luniver Press, pp.148, 2010.
     Google Scholar
  13. L. Bianchi, M. Dorigo, L. M. Gambardella and W. J. Gutjahr, “A survey on metaheuristics for stochastic combinatorial optimization,” Natural Computing 8, 239–287, 2009. doi: 10.1007/s11047-008-9098-4.
     Google Scholar
  14. T. M. Khoshgoftaar, J. V. Hulse and A. Napolitano, “Supervised Neural Network Modeling: An Empirical Investigation Into Learning From Imbalanced Data With Labeling Errors,” IEEE Transactions on Neural Networks 21 (5), 813 – 830, 2010. doi: 10.1109/TNN.2010.2042730.
     Google Scholar
  15. J. W. Lin, “Artificial Neural Network Related to Biological Neuron Network: A Review,” Advanced Studies in Medical Sciences 5(1), 55-62, 2017. doi: 10.12988/asms.2017.753.
     Google Scholar
  16. P. Legendre, and H. J. B. Birks, "From Classical to Canonical Ordination," in Tracking Environmental Change Using Lake Sediments: Data Handling and Numerical Techniques, 201-248, 2012. doi:10.1007/978-94-007-2745-8_8
     Google Scholar
  17. J. W. Lin, “Is it possible to trace an impending earthquake's occurrence from seismo-ionospheric disturbance using principal component analysis? A study of Japan's Iwate-Miyagi Nairiku earthquake on 13 June 2008,” Computers & Geosciences, 37 (7), 855-860, 2011. doi: 10.1016/j.cageo.2011.02.004.
     Google Scholar
  18. I. Koch, “Analysis of multivariate and high-dimensional data,” (Vol. 32). Cambridge University Press, 2013.
     Google Scholar
  19. J. W. Lin, “Rainfall-triggered ordinary earthquakes in Taiwan: a statistical analysis,” Hydrological Sciences Journal 59 (5), 1074-1080, 2014. doi: 10.1080/02626667.2014.900177.
     Google Scholar
  20. D. P. Christopher, 2005, “Physics Made Simple: A Complete Introduction to the Basic Principles of This Fundamental Science,” The Crown Publishing Group pp.208.
     Google Scholar
  21. C. Correns, “G. Mendel’s law concerning the behavior of progeny of varietal hybrids,” Genetics 35(5), part 2, 33-41, 1950.
     Google Scholar
  22. R. C. Punnett, “Early days of genetics,” Heredity 4, 1–10, 1950. doi: 10.1038/hdy.1950.1.
     Google Scholar
  23. I. Miko, “Gregor Mendel and the principles of inheritance,” Nature Education 1(1):134, 2008.
     Google Scholar
  24. E. C. Solomon, D. W. Martin, L. R. Berg, 2015, “Biology,” 10th Edition, Cengage Learning, pp.1440, 2015.
     Google Scholar
  25. J. W. Lin, C. T. Chao, and J. S. Chiou, “Determining Neuronal Number in Each Hidden Layer Using Earthquake Catalogues as Training Data in Training an Embedded Back Propagation Neural Network for Predicting Earthquake Magnitude,” IEEE Access 6, 52582 – 52597, 2018. doi: 10.1109/ACCESS.2018.2870189.
     Google Scholar
  26. M. Friend, N. B. Goethe, and V. S. Harizanov, “Induction, Algorithmic Learning Theory, and Philosophy,” Springer Netherlands, pp.290, 2007. doi: 10.1007/978-1-4020-6127-1.
     Google Scholar
  27. P. N. Johnson-Laird and R. M. J. Byrne, “Deduction (Essays in Cognitive Psychology),” ‎ Psychology Press pp.256, 1991.
     Google Scholar
  28. J. Stoer and R. Bulirsch, “Introduction to Numerical Analysis,” 12, 746, Springer Science & Business Media, 2013.
     Google Scholar