unify

Related work

The foundational work on continual learning, 1980 to 2026: methods, theory, benchmarks, surveys, and the neuroscience of memory. Updated weekly; some carry our notes.

119 papers of 8,653 · showing 101–119Sort Recent · Most cited
IJCNN All papers Clear all
  1. 2019
    Preempting Catastrophic Forgetting in Continual Learning Models by Anticipatory RegularizationAlaa El Khatib, Fakhri KarrayIJCNN · University of Waterloo
  2. 2019
    Stable Network MorphismTao Wei, Changhu Wang, Chang Wen ChenIJCNN · University at Buffalo, State University of New York · Chinese University of Hong Kong, Shenzhen
  3. 2019
    Spatial Map Learning with Self-Organizing Adaptive Recurrent Incremental NetworkWei Hong Chin, Naoyuki Kubota, Chu Kiong Loo … Honghai LiuIJCNN · Tokyo Metropolitan University · University of Malaya · +1
  4. 2019
    Selective Hypothesis Transfer for Lifelong LearningDiana Benavides‐Prado, Yun Sing Koh, Patricia RiddleIJCNN · University of Auckland
  5. 2018
    Adaptive Incremental Gaussian Mixture Network for Non-Stationary Data Stream ClassificationJorge C. Chamby-Diaz, Mariana Recamonde‐Mendoza, Ana L. C. Bazzan, Ricardo GrunitzkiIJCNN · Universidade Federal do Rio Grande do Sul
  6. 2018
    Analysis of inner structure of VSF-NetworkYoshitsugu Kakemoto, Shinichi NakasukaIJCNN · The University of Tokyo
  7. 2017
    Incremental learning with the minimum description length principlePierre-Alexandre Murena, Antoine Cornuéjols, Jean-Louis DessallesIJCNN · Télécom Paris · Université Paris-Saclay
  8. 2017
    Neurogenesis Deep LearningAuthors pendingIJCNN
  9. 2015
    Reduction of catastrophic forgetting with transfer learning and ternary output codesSteven Gutstein, Ethan StumpIJCNN · DEVCOM Army Research Laboratory
  10. 2014
    Efficient class incremental learning for multi-label classification of evolving data streamsZhongwei Shi, Yun Xue, Yimin Wen, Guoyong CaiIJCNN · Guilin University of Electronic Technology · Hunan City University
  11. 2013
    Mitigation of catastrophic forgetting in recurrent neural networks using a Fixed Expansion LayerRobert Coop, Itamar ArelIJCNN · University of Tennessee at Knoxville
  12. 2012
    Using a Gaussian mixture neural network for incremental learning and roboticsMilton Roberto Heinen, Paulo Martins Engel, Rafael PintoIJCNN · Universidade do Estado de Santa Catarina · Universidade Federal do Rio Grande do Sul
  13. 2010
    An incremental learning method for neural networks in adaptive environmentsBeatriz Pérez‐Sánchez, Óscar Fontenla-Romero, Bertha Guijarro‐BerdiñasIJCNN · Universidade da Coruña
  14. 2008
    A comparison of fuzzy ARTMAP and Gaussian ARTMAP neural networks for incremental learningÉric Granger, Jean-François Connolly, Robert SabourinIJCNN · École de Technologie Supérieure
  15. 2004
    Incremental learning in dynamic environments using neural network with long-term memoryK. Tsumori, Seiichi OzawaIJCNN · Kobe University
  16. 2003
    Learn++: a classifier independent incremental learning algorithm for supervised neural networksRobi Polikar, J. Byorick, Stefanie Krause … M. MoretonIJCNN · Rowan University
  17. 1999
    Pattern classification by an incremental learning fuzzy neural networkGary G. Yen, Phayung MeesadIJCNN · Oklahoma State University
  18. 1991
    Incremental learning with rule-based neural networksCharles M. Higgins, R.M. GoodmanIJCNN · California Institute of Technology
  19. 2002
    Reducing computations in incremental learning for feedforward neural network with long-term memoryM. Kobyashi, Abu Sarwar Zamani, Seiichi Ozawa, Shigeo AbeIJCNN · Kobe University
About this index

We keep this list because we read the field and wanted one place to see it. It covers work on continual learning itself, in the core areas of machine learning, and leaves out papers that apply it inside another field, such as medical imaging or fault diagnosis. By default it shows the papers we have a reason to trust: published at a venue like NeurIPS, ICML, ICLR, CVPR or TPAMI, or written by someone who has published there, or cited a few hundred times. The rest are one click away under “All papers”. It is seeded from the community lists kept by ContinualAI and by Xialei Liu, then filled out from OpenAlex, and every week a script looks for new papers on OpenAlex and arXiv. A model reads each candidate and decides whether it belongs; a person reviews the additions before they go live. Authors and affiliations come from OpenAlex, so a recent preprint can lack its institutions for a week or two.

Missing something, or filed under the wrong venue? Write to hello@unify.ai with the arXiv id or DOI.