Environmental Adaptation and Differential Replication in Machine Learning

Entropy

Irene Unceta¹  Oriol Pujol²  Jordi Nin³ 

[1] BBVA Data & Analytics, 28050 Madrid, Spain;Department of Mathematics and Computer Science, Universitat de Barcelona, 08007 Barcelona, Spain;Department of Operations, Innovation and Data Sciences, Universitat Ramon Llull, ESADE, 08172 Sant Cugat del Vallès, Spain;

关键词: natural selection;    differential replication;    machine learning;    knowledge distillation;    editing;    copying;   

DOI  :  10.3390/e22101122

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown