TY - JOUR
T1 - Biological underpinnings for lifelong learning machines
AU - Kudithipudi, Dhireesha
AU - Aguilar-Simon, Mario
AU - Babb, Jonathan
AU - Bazhenov, Maxim
AU - Blackiston, Douglas
AU - Bongard, Josh
AU - Brna, Andrew P.
AU - Chakravarthi Raja, Suraj
AU - Cheney, Nick
AU - Clune, Jeff
AU - Daram, Anurag
AU - Fusi, Stefano
AU - Helfer, Peter
AU - Kay, Leslie
AU - Ketz, Nicholas
AU - Kira, Zsolt
AU - Kolouri, Soheil
AU - Krichmar, Jeffrey L.
AU - Kriegman, Sam
AU - Levin, Michael
AU - Madireddy, Sandeep
AU - Manicka, Santosh
AU - Marjaninejad, Ali
AU - McNaughton, Bruce
AU - Miikkulainen, Risto
AU - Navratilova, Zaneta
AU - Pandit, Tej
AU - Parker, Alice
AU - Pilly, Praveen K.
AU - Risi, Sebastian
AU - Sejnowski, Terrence J.
AU - Soltoggio, Andrea
AU - Soures, Nicholas
AU - Tolias, Andreas S.
AU - Urbina-Meléndez, Darío
AU - Valero-Cuevas, Francisco J.
AU - van de Ven, Gido M.
AU - Vogelstein, Joshua T.
AU - Wang, Felix
AU - Weiss, Ron
AU - Yanguas-Gil, Angel
AU - Zou, Xinyun
AU - Siegelmann, Hava
N1 - Funding Information:
This work was partly supported by the DARPA Lifelong Learning Machines programme. We wish to express our thanks to the technical leadership team of DARPA L2M, specifically R. McFarland, B. Epstein, R. McFarland and T. Senator. R. McFarland and B. Epstein offered several insights on organization of the paper, contributed in brainstorming sessions, and provided graphics suggestions. T. Senator seeded the idea to develop a review article. R. McFarland and other members of the L2M team spurred insightful discussions and provided feedback on the Perspective. We thank G. Vallabha, E. Johnson, M. Peot, F. Sha for reviewing the manuscript.
Publisher Copyright:
© 2022, Springer Nature Limited.
PY - 2022/3
Y1 - 2022/3
N2 - Biological 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.
AB - Biological 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.
UR - http://www.scopus.com/inward/record.url?scp=85127349740&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85127349740&partnerID=8YFLogxK
U2 - 10.1038/s42256-022-00452-0
DO - 10.1038/s42256-022-00452-0
M3 - Review article
AN - SCOPUS:85127349740
SN - 2522-5839
VL - 4
SP - 196
EP - 210
JO - Nature Machine Intelligence
JF - Nature Machine Intelligence
IS - 3
ER -