Sustainable Artificial Intelligence through Continual Learning

Andrea Cossu; Marta Ziosi; Vincenzo Lomonaco

Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI, CAIP 2021, 20-24 November 2021, Bologna, Italy

Research Article

Sustainable Artificial Intelligence through Continual Learning

Download313 downloads

Cite: BibTeX Plain Text

@INPROCEEDINGS{10.4108/eai.20-11-2021.2314097,
    author={Andrea  Cossu and Marta  Ziosi and Vincenzo  Lomonaco},
    title={Sustainable Artificial Intelligence through Continual Learning},
    proceedings={Proceedings of the 1st International Conference on AI for People: Towards Sustainable AI, CAIP 2021, 20-24 November 2021, Bologna, Italy},
    publisher={EAI},
    proceedings_a={CAIP},
    year={2021},
    month={12},
    keywords={sustainable-ai continual-learning lifelong-learning},
    doi={10.4108/eai.20-11-2021.2314097}
}

Andrea Cossu
Marta Ziosi
Vincenzo Lomonaco
Year: 2021
Sustainable Artificial Intelligence through Continual Learning
CAIP
EAI
DOI: 10.4108/eai.20-11-2021.2314097

Andrea Cossu¹^,*, Marta Ziosi², Vincenzo Lomonaco¹

1: University of Pisa
2: University of Oxford

*Contact email: andrea.cossu@sns.it

Abstract

The increasing attention on Artificial Intelligence (AI) regulamentation has led to the definition of a set of ethical principles grouped into the Sustainable AI framework. In this article, we identify Continual Learning, an active area of AI research, as a promising approach towards the design of systems compliant with the Sustainable AI principles. While Sustainable AI outlines general desiderata for ethical applications, Continual Learning provides means to put such desiderata into practice.

Keywords: sustainable-ai continual-learning lifelong-learning

Published: 2021-12-13
Publisher: EAI

: http://dx.doi.org/10.4108/eai.20-11-2021.2314097