Continual Learning through Hamilton Equations

Autor: Betti, Alessandro, Faggi, Lapo, Gori, Marco, Tiezzi, Matteo, Marullo, Simone, Meloni, Enrico, Melacci, Stefano
Přispěvatelé: Université Côte d'Azur (UCA), Modèles et algorithmes pour l’intelligence artificielle (MAASAI), Inria Sophia Antipolis - Méditerranée (CRISAM), Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Laboratoire Jean Alexandre Dieudonné (LJAD), Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Scalable and Pervasive softwARe and Knowledge Systems (Laboratoire I3S - SPARKS), Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Université Nice Sophia Antipolis (1965 - 2019) (UNS), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Laboratoire d'Informatique, Signaux, et Systèmes de Sophia Antipolis (I3S), COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-COMUE Université Côte d'Azur (2015-2019) (COMUE UCA)-Centre National de la Recherche Scientifique (CNRS)-Université Côte d'Azur (UCA)-Centre National de la Recherche Scientifique (CNRS), Università degli Studi di Firenze = University of Florence (UniFI), Dipartimento di Ingegneria dell'Informazione [Firenze] (DINFO), Università degli Studi di Siena = University of Siena (UNISI), Department of Information engineering and mathematics [Siena], Dipartimento di Ingegneria dell'informazione e scienze matematiche [Siena] (DIISM), ANR-19-P3IA-0002,3IA@cote d'azur,3IA Côte d'Azur(2019)
Jazyk: angličtina
Rok vydání: 2022
Předmět:
Zdroj: Proceedings of Machine Learning Research
CoLLAs 2022-Conference on Lifelong Learning Agents
CoLLAs 2022-Conference on Lifelong Learning Agents, Aug 2022, Montreal, Canada
Popis: International audience; Learning in a continual manner is one of the main challenges that the machine learning community is currently facing. The importance of the problem can be readily understood as soon as we consider settings where an agent is supposed to learn through an online interaction with a data stream, rather than operating offline on previously prepared data collections. In the last few years many efforts have been spent in proposing both models and algorithms to let machines learn in a continual manner, and the problem still remains extremely challenging. Many of the existing works rely on re-adapting the usual learning framework inherited from classic statistical approaches, that are typical of noncontinual-learning oriented problems. In this paper we consider a fully new perspective, rethinking the methodologies to be used to tackle continual learning, instead of re-adapting offline-oriented optimization. In particular, we propose a novel method to frame continual and online learning within the framework of optimal control. The proposed formulation leads to a novel interpretation of learning dynamics in terms of Hamilton equations. As a case study for the theory, we consider the problem of unsupervised optical flow estimation from a video stream. An experimental proof of concept for this learning task is discussed with the purpose of illustrating the soundness of the proposed approach, and opening to further research in this direction.
Databáze: OpenAIRE
Externí odkaz: