A Conceptual Framework for Lifelong Learning

Humans can learn a variety of concepts and skills incrementally over the course of their lives while exhibiting many desirable properties, such as continual learning without forgetting, forward transfer and backward transfer of knowledge, and learning a new concept or task with only a few examples. Several lines of machine learning research, such as lifelong learning, few-shot learning, and transfer learning, attempt to capture these properties. However, most previous approaches can only demonstrate subsets of these properties, often by different complex mechanisms. In this work, we propose a simple yet powerful unified framework that supports almost all of these properties and approaches through one central mechanism. We also draw connections between many peculiarities of human learning (such as memory loss and "rain man") and our framework. While we do not present any state-of-the-art results, we hope that this conceptual framework provides a novel perspective on existing work and proposes many new research directions.

[1]  Timothy M. Hospedales,et al.  Meta-Learning in Neural Networks: A Survey , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Brendan McCane,et al.  Pseudo-Recursal: Solving the Catastrophic Forgetting Problem in Deep Neural Networks , 2018, ArXiv.

[3]  B. McEwen,et al.  Stress, sex, and neural adaptation to a changing environment: mechanisms of neuronal remodeling , 2010, Annals of the New York Academy of Sciences.

[4]  Yoshua Bengio,et al.  Why Does Unsupervised Pre-training Help Deep Learning? , 2010, AISTATS.

[5]  S. Ackerman Discovering the brain , 1992 .

[6]  Kaiming He,et al.  Exploring the Limits of Weakly Supervised Pretraining , 2018, ECCV.

[7]  Marc'Aurelio Ranzato,et al.  Gradient Episodic Memory for Continual Learning , 2017, NIPS.

[8]  Sebastian Thrun,et al.  A lifelong learning perspective for mobile robot control , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[9]  Michael Carbin,et al.  The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks , 2018, ICLR.

[10]  Charles Ling,et al.  A Deeper Look at Bongard Problems , 2020, Canadian Conference on AI.

[11]  Joachim Denzler,et al.  Fine-Tuning Deep Neural Networks in Continuous Learning Scenarios , 2016, ACCV Workshops.

[12]  Matthew P Walker,et al.  Sleep, memory and emotion. , 2010, Progress in brain research.

[13]  Bram van Ginneken,et al.  A survey on deep learning in medical image analysis , 2017, Medical Image Anal..

[14]  Kyunghyun Cho,et al.  Continual Learning via Neural Pruning , 2019, ArXiv.

[15]  Trevor Darrell,et al.  Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation , 2013, 2014 IEEE Conference on Computer Vision and Pattern Recognition.

[16]  Honglak Lee,et al.  Zero-Shot Task Generalization with Multi-Task Deep Reinforcement Learning , 2017, ICML.

[17]  William D S Killgore,et al.  Effects of sleep deprivation on cognition. , 2010, Progress in brain research.

[18]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[19]  Richard Socher,et al.  Learn to Grow: A Continual Structure Learning Framework for Overcoming Catastrophic Forgetting , 2019, ICML.

[20]  Larry P. Heck,et al.  Class-incremental Learning via Deep Model Consolidation , 2019, 2020 IEEE Winter Conference on Applications of Computer Vision (WACV).

[21]  C. Sisk,et al.  Pubertal hormones organize the adolescent brain and behavior , 2005, Frontiers in Neuroendocrinology.

[22]  Razvan Pascanu,et al.  Overcoming catastrophic forgetting in neural networks , 2016, Proceedings of the National Academy of Sciences.

[23]  Samy Bengio,et al.  Understanding deep learning requires rethinking generalization , 2016, ICLR.

[24]  Kilian Q. Weinberger,et al.  Densely Connected Convolutional Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[25]  Jaime G. Carbonell,et al.  Characterizing and Avoiding Negative Transfer , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[26]  Jiwon Kim,et al.  Continual Learning with Deep Generative Replay , 2017, NIPS.

[27]  Anthony V. Robins,et al.  Catastrophic Forgetting, Rehearsal and Pseudorehearsal , 1995, Connect. Sci..

[28]  Stefan Wermter,et al.  Continual Lifelong Learning with Neural Networks: A Review , 2019, Neural Networks.

[29]  Geoffrey E. Hinton,et al.  Matrix capsules with EM routing , 2018, ICLR.

[30]  Abhinav Gupta,et al.  Unsupervised Learning of Visual Representations Using Videos , 2015, 2015 IEEE International Conference on Computer Vision (ICCV).

[31]  Tiago Ramalho,et al.  An empirical study of pretrained representations for few-shot classification , 2019, ArXiv.

[32]  Marcus Rohrbach,et al.  Memory Aware Synapses: Learning what (not) to forget , 2017, ECCV.

[33]  Zhanxing Zhu,et al.  Reinforced Continual Learning , 2018, NeurIPS.

[34]  Heung-Il Suk,et al.  Deep Learning in Medical Image Analysis. , 2017, Annual review of biomedical engineering.

[35]  Matthias De Lange,et al.  Continual learning: A comparative study on how to defy forgetting in classification tasks , 2019, ArXiv.

[36]  Pietro Perona,et al.  One-shot learning of object categories , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[37]  Joshua B. Tenenbaum,et al.  Human-level concept learning through probabilistic program induction , 2015, Science.

[38]  Marc'Aurelio Ranzato,et al.  Continual Learning with Tiny Episodic Memories , 2019, ArXiv.

[39]  David Isele,et al.  Selective Experience Replay for Lifelong Learning , 2018, AAAI.

[40]  Eric Eaton,et al.  ELLA: An Efficient Lifelong Learning Algorithm , 2013, ICML.

[41]  John K. Tsotsos,et al.  Intriguing Properties of Randomly Weighted Networks: Generalizing While Learning Next to Nothing , 2018, 2019 16th Conference on Computer and Robot Vision (CRV).

[42]  Jason Weston,et al.  Curriculum learning , 2009, ICML '09.

[43]  Derek Hoiem,et al.  Learning without Forgetting , 2016, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[44]  Erich D. Jarvis,et al.  Brain evolution by brain pathway duplication , 2015, Philosophical Transactions of the Royal Society B: Biological Sciences.

[45]  P. S. St George-Hyslop,et al.  Prediction of probable Alzheimer's disease in memory-impaired patients , 1996, Neurology.

[46]  Philip H. S. Torr,et al.  Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigence , 2018, ECCV.

[47]  Guillermo Sapiro,et al.  Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy? , 2015, IEEE Transactions on Signal Processing.

[48]  Qiang Yang,et al.  A Survey on Transfer Learning , 2010, IEEE Transactions on Knowledge and Data Engineering.

[49]  Tinne Tuytelaars,et al.  Task-Free Continual Learning , 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[50]  Surya Ganguli,et al.  Continual Learning Through Synaptic Intelligence , 2017, ICML.

[51]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[52]  Sung Ju Hwang,et al.  Lifelong Learning with Dynamically Expandable Networks , 2017, ICLR.

[53]  Will Kanyusik The Problem of Recognition: The Disabled Male Veteran and Masculinity as Spectacle in William Wyler's The Best Years of Our Lives , 2012 .

[54]  Yu Zhang,et al.  A Survey on Multi-Task Learning , 2017, IEEE Transactions on Knowledge and Data Engineering.

[55]  Michael S. Gazzaniga,et al.  Nature's Mind: The Biological Roots of Thinking, Emotions, Sexuality, Language, and Intelligence, Michael S. Gazzaniga. 1992. Basic Books, Inc. Publishers, New York, NY. 256 pages. ISBN: 0-465-07-649-1. $25.00 , 1992 .

[56]  Gan Sun,et al.  Active Lifelong Learning With "Watchdog" , 2018, AAAI.

[57]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[58]  Demis Hassabis,et al.  Mastering the game of Go without human knowledge , 2017, Nature.

[59]  Geoffrey E. Hinton,et al.  Dynamic Routing Between Capsules , 2017, NIPS.

[60]  H.L.J. van der Maas,et al.  On the Nature and Nurture of Intelligence and Specific Cognitive Abilities , 2013, Psychological science.

[61]  David Barber,et al.  Online Structured Laplace Approximations For Overcoming Catastrophic Forgetting , 2018, NeurIPS.

[62]  Yuandong Tian,et al.  One ticket to win them all: generalizing lottery ticket initializations across datasets and optimizers , 2019, NeurIPS.

[63]  Gerald Tesauro,et al.  Learning to Learn without Forgetting By Maximizing Transfer and Minimizing Interference , 2018, ICLR.

[64]  A. M. Leahy Nature-nurture and intelligence. , 1935 .

[65]  Hal Daumé,et al.  Learning Task Grouping and Overlap in Multi-task Learning , 2012, ICML.

[66]  J. Elman Learning and development in neural networks: the importance of starting small , 1993, Cognition.

[67]  Patrick Jähnichen,et al.  Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learning , 2019, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

[68]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[69]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[70]  Andrea Bonarini,et al.  Sharing Knowledge in Multi-Task Deep Reinforcement Learning , 2020, ICLR.

[71]  Michael S. Bernstein,et al.  ImageNet Large Scale Visual Recognition Challenge , 2014, International Journal of Computer Vision.

[72]  Lorenzo Rosasco,et al.  Generalization Properties of Learning with Random Features , 2016, NIPS.

[73]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[74]  Holger Schwenk,et al.  Supervised Learning of Universal Sentence Representations from Natural Language Inference Data , 2017, EMNLP.

[75]  Geoffrey I. Webb,et al.  Characterizing concept drift , 2015, Data Mining and Knowledge Discovery.

[76]  Eric Eaton,et al.  Active Task Selection for Lifelong Machine Learning , 2013, AAAI.