Direct Use of Neural Networks for Decision Making

In most cases the output of a neural network produces a predicted value for the relevant output factor or probabilities for different values of the relevant output factor, and a decision is made based on these values.This paper develops a methodology of using neural networks directly for making decisions without preliminary obtaining the predicted value for the relevant output factor (or probabilities fordifferent values of the relevant output factor). The presented methodology is related to reinforcement learning.

Content

Author and article information

Journal

Title: ScienceOpen Preprints

Publisher: ScienceOpen

Publication date (Electronic preprint): 31 July 2020

Affiliations

[1 ] Professor at Department of Mathematical Methods in Economics, Belarus State Economic University (Minsk, Belarus)

Author information

Ernest Aksen https://orcid.org/0000-0001-6627-8521

Article

DOI: 10.14293/S2199-1006.1.SOR-.PPDOPZQ.v1

SO-VID: ecc26c85-94a9-4e4c-ae33-b8c09b0a0b6a

License:

This work has been published open access under Creative Commons Attribution License CC BY 4.0 , which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Conditions, terms of use and publishing policy can be found at www.scienceopen.com .

History

Date received : 31 July 2020

Data availability: All data generated or analysed during this study are included in this published article (and its supplementary information files).

ScienceOpen disciplines: Mathematical software,Numerical methods,Machine learning,Neural & Evolutionary computing,Artificial intelligence,Mathematical economics,Mathematical modeling & Computation

Keywords: nearal network, decision making, parameters

One-Click Submission System Now Available for SO Preprints, learn more on how this works in our blog post and don't forget to check the video, too!