Biological underpinnings for lifelong learning machines
Dhireesha Kudithipudi,Mario Aguilar-Simon,Jonathan Babb,Maxim Bazhenov,Douglas J. Blackiston,Josh C. Bongard,Andrew Brna,Suraj Chakravarthi Raja,Nick Cheney,Jeff Clune,Anurag Reddy Daram,S. Fusi,Peter Helfer,Leslie Kay,Nicholas A. Ketz,Zsolt Kira,Soheil Kolouri,Jeffrey L. Krichmar,Sam Kriegman,Michael Levin,Sandeep Reddy Madireddy,Santosh Manicka,Ali Marjaninejad,Bruce L. McNaughton,Risto Miikkulainen,Zaneta Navratilova,Tej Pandit,Alice Virginia Parker,Praveen K. Pilly,Sebastian Risi,Terrence J. Sejnowski,Andrea 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 T. Siegelmann +42 more
TL;DR: Kudithipudi et al. as mentioned in this paper identified a set of key capabilities that artificial systems will need to achieve lifelong learning, and discussed pathways to developing biologically inspired approaches for lifelong learning machines.
read more
Abstract: 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. It is an outstanding challenge to develop intelligent machines that can learn continually from interactions with their environment, throughout their lifetime. Kudithipudi et al. review neuronal and non-neuronal processes in organisms that address this challenge and discuss pathways to developing biologically inspired approaches for lifelong learning machines.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Three types of incremental learning
TL;DR: In this article , the authors describe three fundamental types of continual learning: task-incremental, domain-increasing and class-increasing learning, and provide a comprehensive empirical comparison of currently used continual learning strategies.
A Comprehensive Survey of Continual Learning: Theory, Method and Application
TL;DR: A comprehensive survey of continual learning can be found in this article , where the authors summarize the general objectives of continuous learning as ensuring a proper stability-plasticity trade-off and an adequate intra/inter-task generalizability in the context of resource efficiency.
Video PreTraining (VPT): Learning to Act by Watching Unlabeled Online Videos
B. Baker,Ilge Akkaya,P. A. Zhokhov,Joost Huizinga,Jie Tang,Adrien Ecoffet,Brandon Houghton,Raul Sampedro,Jeff Clune +8 more
- 23 Jun 2022
TL;DR: This work extends the internet-scale pretraining paradigm to sequential decision domains through semi-supervised imitation learning wherein agents learn to act by watching online unlabeled videos, and is the first to report computer agents that can craft diamond tools.
A Comprehensive Survey of Continual Learning: Theory, Method and Application
Liyuan Wang,Xingxing Zhang,Hang Su,Jun Zhu +3 more
TL;DR: A comprehensive survey of continual learning covering theory, method and application. The survey explores the challenges and opportunities associated with continual learning, including catastrophic forgetting and resource efficiency. It also provides a detailed taxonomy of representative strategies and their adaptation to various applications.
133
Battery safety: Machine learning-based prognostics
Jingyuan Zhao,Xuning Feng,Quanquan Pang,Michael Fowler,Yubo Lian,Minggao Ouyang,Andrew F. Burke +6 more
TL;DR: This review explores machine learning-based prognostics for lithium-ion battery safety, covering mechanisms of failure, predictive models, and fault diagnosis techniques, including supervised, unsupervised, and few-shot learning, to enhance battery reliability and prevent catastrophic events.
49
References
•Posted Content
DisCoRL: Continual Reinforcement Learning via Policy Distillation.
René Traoré,Hugo Caselles-Dupré,Timothée Lesort,Te Sun,Guanghang Cai,Natalia Díaz-Rodríguez,David Filliat +6 more
TL;DR: This paper proposes DisCoRL, an approach combining state representation learning and policy distillation that can solve all tasks and automatically infer which one to run, and tests its robustness by transferring the final policy into a real life setting.
Neuromorphic meets neuromechanics, part II: the role of fusimotor drive.
Kian Jalaleddini,Chuanxin M. Niu,Suraj Chakravarthi Raja,Won Joon Sohn,Gerald E. Loeb,Terence D. Sanger,Francisco J. Valero-Cuevas +6 more
TL;DR: It is demonstrated that fundamental features of spinal afferentation sufficed to produce muscle function and is a viable platform to study the spinal mechanisms for healthy muscle function-and its pathologies such as dystonia and spasticity.
Retention of Memory through Metamorphosis: Can a Moth Remember What It Learned As a Caterpillar?
TL;DR: The present study is the first to demonstrate conclusively that associative memory survives metamorphosis in Lepidoptera, and provokes intriguing new questions about the organization and persistence of the central nervous system during meetamorphosis.
Layering as optimization decomposition: A mathematical theory of network architectures : There are various ways that network functionalities can be allocated to different layers and to different network elements, some being more desirable than others. The intellectual goal of the research surveyed by this article is to provide a theoretical foundation for these architectural decisions in networking
Mung Chiang,Steven H. Low,A. Robert Calderbank,John Doyle +3 more
- 01 Jan 2007
TL;DR: A survey of the recent efforts towards a systematic understanding of layering as optimization decomposition, where the overall communication network is modeled by a generalized network utility maximization problem, each layer corresponds to a decomposed subproblem, and the interfaces among layers are quantified as functions of the optimization variables coordinating the subproblems.
Reward probability and timing uncertainty alter the effect of dorsal raphe serotonin neurons on patience.
Katsuhiko Miyazaki,Kayoko W. Miyazaki,Akihiro Yamanaka,Tomoki Tokuda,Kenji F. Tanaka,Kenji Doya +5 more
TL;DR: It is shown that serotonin effect in promoting waiting is maximized by both high probability and high timing uncertainty of reward, suggesting that it boosts the prior probability of reward.