This is a Preprint and has not been peer reviewed. This is version 3 of this Preprint.
Downloads
Authors
Abstract
In this brief communication, biomolecular plant breeding multi-classification inference is discussed when leveraging the advantages of Physics-informed Neural Network (PiNN) architecture. Albeit, the expected utility of Partial Differential Equation (PDE) inspired neural networks resides in its performance under limited data availability; a variety of neural network configurations result from PDE inspired machine learning models. Having less emphasis on the theoretical outcomes of the PiNN while paying particular attention to the performance of the model prior to convergence. Biotechnology stands to experience myriad benefits as both plant science and machine learning evolve and cross-pollinate.
DOI
https://doi.org/10.31223/X53P9N
Subjects
Artificial Intelligence and Robotics, Climate, Other Statistics and Probability, Plant Sciences, Probability, Quantum Physics, Research Methods in Life Sciences, Soil Science, Statistical, Nonlinear, and Soft Matter Physics, Sustainability, Systems Biology
Keywords
Plant science | quantum machine learning | partial differential equations | Qbism | Biomolecular, plant science, biomolecular, quantum bayesianism, Partial differential equations
Dates
Published: 2022-08-31 13:56
Last Updated: 2023-03-13 09:03
Older Versions
License
CC BY Attribution 4.0 International
Additional Metadata
Conflict of interest statement:
None
Data Availability (Reason not available):
This is a brief communication absent analysis in this current form.
There are no comments or no comments have been made public for this article.