Nature_Bio_L2M_Revision_2.pdf (2.18 MB)
Biological underpinnings for lifelong learning machines
journal contribution
posted on 2022-03-31, 13:08 authored by Dhireesha Kudithipudi, Mario Aguilar-Simon, Jonathan Babb, Maxim Bazhenov, Douglas Blackiston, Josh Bongard, Andrew P Brna, Suraj Chakravarthi Raja, Nick Cheney, Jeff Clune, Anurag Daram, Stefano Fusi, Peter Helfer, Leslie Kay, Nicholas Ketz, Zsolt Kira, Soheil Kolouri, Jeffrey L Krichmar, Sam Kriegman, Michael Levin, Sandeep Madireddy, Santosh Manicka, Ali Marjaninejad, Bruce McNaughton, Risto Miikkulainen, Zaneta Navratilova, Tej Pandit, Alice Parker, Praveen K Pilly, Sebastian Risi, Terrence J Sejnowski, Andrea SoltoggioAndrea Soltoggio, Nicholas Soures, Andreas S Tolias, Darío Urbina-Meléndez, Francisco J Valero-Cuevas, Gido M van de Ven, Joshua T Vogelstein, Felix Wang, Ron Weiss, Angel Yanguas-Gil, Xinyun Zou, Hava SiegelmannBiological organisms learn from interactions with their environment throughout their lifetime. For artificial systems to successfully act and adapt in the real world, it is desirable to similarly be able to learn on a continual basis. This challenge is known as lifelong learning, and remains to a large extent unsolved. In this Perspective article, we identify a set of key capabilities that artificial systems will need to achieve lifelong learning. We describe a number of biological mechanisms, both neuronal and non-neuronal, that help explain how organisms solve these challenges, and present examples of biologically inspired models and biologically plausible mechanisms that have been applied to artificial systems in the quest towards development of lifelong learning machines. We discuss opportunities to further our understanding and advance the state of the art in lifelong learning, aiming to bridge the gap between natural and artificial intelligence.
Funding
DARPA Lifelong Learning Machines programme
History
School
- Science
Department
- Computer Science
Published in
Nature Machine IntelligenceVolume
4Issue
3Pages
196 - 210Publisher
Springer NatureVersion
- AM (Accepted Manuscript)
Rights holder
© Springer NaturePublisher statement
This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1038/s42256-022-00452-0Acceptance date
2022-01-20Publication date
2022-03-23Copyright date
2022eISSN
2522-5839Publisher version
Language
- en