Framing Lifelong Learning as Autonomous Deployment: Tune Once Live Forever

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 Eu-ropean projects funded under the CHIST-ERA framework on several domains of application.
Document type :
Conference papers
Complete list of metadatas

Cited literature [11 references]  Display  Hide  Download

https://hal.archives-ouvertes.fr/hal-02280158
Contributor : Anthony Larcher <>
Submitted on : Friday, September 6, 2019 - 9:57:14 AM
Last modification on : Saturday, September 7, 2019 - 1:09:50 AM

File

IWSDS___Position_paper_Chister...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-02280158, version 1

Collections

Citation

Eneko Agirre, Anders Jonsson, Anthony Larcher. Framing Lifelong Learning as Autonomous Deployment: Tune Once Live Forever. International Workshop on Spoken Dialogue Systems Technology, Apr 2019, Siracusa, Italy. ⟨hal-02280158⟩

Share

Metrics

Record views

14

Files downloads

7