mlsanityData to 7 Oct 2026

Reviewing continual learning from the perspective of human-level intelligence

arXiv 2111.11964 ↗First posted 23 Nov 2021cs.LG cs.AI cs.NEcited by 1

Not on the map. Why?

Abstract (arXiv)

Humans' continual learning (CL) ability is closely related to Stability Versus Plasticity Dilemma that describes how humans achieve ongoing learning capacity and preservation for learned information. The notion of CL has always been present in artificial intelligence (AI) since its births. This paper proposes a comprehensive review of CL. Different from previous reviews that mainly focus on the catastrophic forgetting phenomenon in CL, this paper surveys CL from a more macroscopic perspective based on the Stability Versus Plasticity mechanism. Analogous to biological counterpart, "smart" AI agents are supposed to i) remember previously learned information (information retrospection); ii) infer on new information continuously (information prospection:); iii) transfer useful information (information transfer), to achieve high-level CL. According to the taxonomy, evaluation metrics, algorithms, applications as well as some open issues are then introduced. Our main contributions concern i) rechecking CL from the level of artificial general intelligence; ii) providing a detailed and extensive overview on CL topics; iii) presenting some novel ideas on the potential development of CL.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 59 of its 155 references that are in the map. First posted on arXiv 23 Nov 2021.

Builds on

59 of 155 references.

References · 59

  1. 2015Distilling the Knowledge in a Neural Networkcited by 10,076
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  5. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  6. 2013Auto-Encoding Variational Bayescited by 3,980
  7. 2016Learning without Forgettingcited by 2,465
  8. 2016iCaRL: Incremental Classifier and Representation Learningcited by 2,313
  9. 2016Matching Networks for One Shot Learningcited by 2,246
  10. 2017Gradient Episodic Memory for Continual Learningcited by 1,871
  11. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  12. 2016Progressive Neural Networkscited by 1,332
38 more
  1. 2017Continual Learning with Deep Generative Replaycited by 1,152
  2. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  3. 2018Efficient Lifelong Learning with A-GEMcited by 1,044
  4. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  5. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  6. 2018Riemannian Walk for Incremental Learning: Understanding Forgetting and Intransigencecited by 734
  7. 2019Large Scale Incremental Learningcited by 727
  8. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  9. 2019Three scenarios for continual learningcited by 610
  10. 2018End-to-End Incremental Learningcited by 596
  11. 2017Generative Adversarial Networks: An Overviewcited by 588
  12. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  13. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  14. 2016Expert Gate: Lifelong Learning with a Network of Expertscited by 369
  15. 2017PathNet: Evolution Channels Gradient Descent in Super Neural Networkscited by 362
  16. 2017Overcoming Catastrophic Forgetting by Incremental Moment Matchingcited by 243
  17. 2017Incremental Learning of Object Detectors without Catastrophic Forgettingcited by 208
  18. 2015DRAW: A Recurrent Neural Network For Image Generationcited by 190
  19. 2019Meta-Learning Representations for Continual Learningcited by 189
  20. 2020Modeling the Background for Incremental Learning in Semantic Segmentationcited by 189
  21. 2019Learning to Remember: A Synaptic Plasticity Driven Framework for Continual Learningcited by 181
  22. 2018Towards Robust Evaluations of Continual Learningcited by 148
  23. 2019Incremental Learning Techniques for Semantic Segmentationcited by 141
  24. 2018Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgettingcited by 127
  25. 2021Semantic-aware Knowledge Distillation for Few-Shot Class-Incremental Learningcited by 114
  26. 2018Generative replay with feedback connections as a general strategy for continual learningcited by 103
  27. 2017Encoder Based Lifelong Learningcited by 102
  28. 2020Incremental Few-Shot Object Detectioncited by 102
  29. 2016Less-forgetting Learning in Deep Neural Networkscited by 97
  30. 2020GAN Memory with No Forgettingcited by 84
  31. 2018Motion Planning Networkscited by 78
  32. 2016AdaNet: Adaptive Structural Learning of Artificial Neural Networkscited by 54
  33. 2019Task Agnostic Continual Learning via Meta Learningcited by 53
  34. 2017Continual Learning in Generative Adversarial Netscited by 51
  35. 2020La-MAML: Look-ahead Meta Learning for Continual Learningcited by 51
  36. 2017A-Fast-RCNN: Hard Positive Generation via Adversary for Object Detectioncited by 43
  37. 2018Incremental Learning for Semantic Segmentation of Large-Scale Remote Sensing Datacited by 35
  38. 2019A comprehensive, application-oriented study of catastrophic forgetting in DNNscited by 35

50 most cited of 59 All 59 (JSON)

Built on by

Cited by year

Citing papers per year: 2022: 1.

1 paper.

  1. 2022Continual Learning of Dynamical Systems with Competitive Federated Reservoir Computingcited by 6