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

Jyh-Woei Lin
Additional contact information
Jyh-Woei Lin: Nanjing University of Information Science & Technology, China

European Journal of Information Technologies and Computer Science, 2021, vol. 1, issue 4, 6-8

Abstract: 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 (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
https://eu-opensci.org/index.php/compute/article/view/10029 Abstract page (text/html)
https://eu-opensci.org/index.php/compute/article/download/10029/1781 Full text (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:epw:comput:v:1:y:2021:i:4:id:10029

DOI: 10.24018/compute.2021.1.4.29

Access Statistics for this article

More articles in European Journal of Information Technologies and Computer Science from European Open Science
Bibliographic data for series maintained by Support Team ().