Framing lifelong learning as autonomous deployment: tune once live forever

Agirre, Eneko; Jonsson, Anders, 1973-; Larcher, Anthony

doi:http://dx.doi.org/10.1007/978-981-15-9323-9_29

Framing lifelong learning as autonomous deployment: tune once live forever

Citation

Agirre E, Jonsson A, Larcher A. Framing lifelong learning as autonomous deployment: tune once live forever. In: Marchi E, Siniscalchi SM, Cumani S, Salerno VM, Li, H, editors. Increasing naturalness and flexibility in spoken dialogue interaction: 10th International Workshop on Spoken Dialogue Systems (IWSDS 2019); 2019 Abr 24-26; Syracuse, Italy. [Singapore]: Springer Singapore; 2021. p. 331-6. DOI: 10.1007/978-981-15-9323-9_29

Abstract

Lifelong Learning in the context of Artificial Intelligence is a new paradigm that is still in its infancy. It refers to agents that are able to learn continuously, accumulating the knowledge learned in previous tasks and using it to help future learning. In this position paper we depart from the focus on learning new tasks and instead take a stance from the perspective of the life-cycle of intelligent software. We propose to focus lifelong learning research on autonomous intelligent systems that sustain their performance after deployment in production across time without the need of machine learning experts. This perspective is being applied to three European projects funded under the CHIST-ERA framework on several domains of application.