Please use this identifier to cite or link to this item: http://hdl.handle.net/2445/174914
Title: Environmental adaptation and differential replication in machine learning
Author: Unceta, Irene
Nin, Jordi
Pujol Vila, Oriol
Keywords: Aprenentatge automàtic
Selecció natural
Machine learning
Natural selection
Issue Date: 3-Oct-2020
Publisher: MDPI
Abstract: When deployed in the wild, machine learning models are usually confronted withan environment that imposes severe constraints. As this environment evolves, so do these constraints.As a result, the feasible set of solutions for the considered need is prone to change in time. We referto this problem as that of environmental adaptation. In this paper, we formalize environmentaladaptation and discuss how it differs from other problems in the literature. We propose solutionsbased on differential replication, a technique where the knowledge acquired by the deployed modelsis reused in specific ways to train more suitable future generations. We discuss different mechanismsto implement differential replications in practice, depending on the considered level of knowledge.Finally, we present seven examples where the problem of environmental adaptation can be solvedthrough differential replication in real-life applications.
Note: Reproducció del document publicat a: https://doi.org/10.3390/e22101122
It is part of: Entropy, 2020, vol. 22, num. 10
URI: http://hdl.handle.net/2445/174914
Related resource: https://doi.org/10.3390/e22101122
ISSN: 1099-4300
Appears in Collections:Articles publicats en revistes (Matemàtiques i Informàtica)

Files in This Item:
File Description SizeFormat 
703534.pdf561.18 kBAdobe PDFView/Open


This item is licensed under a Creative Commons License Creative Commons