Environmental adaptation and differential replication in machine learning

Irene Unceta, Jordi Nin, Oriol Pujol

Producció científica: Article en revista indexadaArticleAvaluat per experts

6 Cites (Scopus)


When deployed in the wild, machine learning models are usually confronted with an 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 refer to this problem as that of environmental adaptation. In this paper, we formalize environmental adaptation and discuss how it differs from other problems in the literature. We propose solutions based on differential replication, a technique where the knowledge acquired by the deployed models is reused in specific ways to train more suitable future generations. We discuss different mechanisms to 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 solved through differential replication in real-life applications.

Idioma originalAnglès
Número d’article1122
Pàgines (de-a)1-14
Nombre de pàgines14
Estat de la publicacióPublicada - d’oct. 2020


Navegar pels temes de recerca de 'Environmental adaptation and differential replication in machine learning'. Junts formen un fingerprint únic.

Com citar-ho