IDEAS home Printed from https://ideas.repec.org/a/plo/pcbi00/1009092.html
   My bibliography  Save this article

Multitask learning over shared subspaces

Author

Listed:
  • Nicholas Menghi
  • Kemal Kacar
  • Will Penny

Abstract

This paper uses constructs from machine learning to define pairs of learning tasks that either shared or did not share a common subspace. Human subjects then learnt these tasks using a feedback-based approach and we hypothesised that learning would be boosted for shared subspaces. Our findings broadly supported this hypothesis with either better performance on the second task if it shared the same subspace as the first, or positive correlations over task performance for shared subspaces. These empirical findings were compared to the behaviour of a Neural Network model trained using sequential Bayesian learning and human performance was found to be consistent with a minimal capacity variant of this model. Networks with an increased representational capacity, and networks without Bayesian learning, did not show these transfer effects. We propose that the concept of shared subspaces provides a useful framework for the experimental study of human multitask and transfer learning.Author summary: How does knowledge gained from previous experience affect learning of new tasks? This question of “Transfer Learning” has been addressed by teachers, psychologists, and more recently by researchers in the fields of neural networks and machine learning. Leveraging constructs from machine learning, we designed pairs of learning tasks that either shared or did not share a common subspace. We compared the dynamics of transfer learning in humans with those of a multitask neural network model, finding that human performance was consistent with a minimal capacity variant of the model. Learning was boosted in the second task if the same subspace was shared between tasks. Additionally, accuracy between tasks was positively correlated but only when they shared the same subspace. Our results highlight the roles of subspaces, showing how they could act as a learning boost if shared, and be detrimental if not.

Suggested Citation

  • Nicholas Menghi & Kemal Kacar & Will Penny, 2021. "Multitask learning over shared subspaces," PLOS Computational Biology, Public Library of Science, vol. 17(7), pages 1-25, July.
  • Handle: RePEc:plo:pcbi00:1009092
    DOI: 10.1371/journal.pcbi.1009092
    as

    Download full text from publisher

    File URL: https://journals.plos.org/ploscompbiol/article?id=10.1371/journal.pcbi.1009092
    Download Restriction: no

    File URL: https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1009092&type=printable
    Download Restriction: no

    File URL: https://libkey.io/10.1371/journal.pcbi.1009092?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    References listed on IDEAS

    as
    1. Nicholas T Franklin & Michael J Frank, 2018. "Compositional clustering in task structure learning," PLOS Computational Biology, Public Library of Science, vol. 14(4), pages 1-25, April.
    2. Shiva Farashahi & Katherine Rowe & Zohra Aslami & Daeyeol Lee & Alireza Soltani, 2017. "Feature-based learning improves adaptability without compromising precision," Nature Communications, Nature, vol. 8(1), pages 1-16, December.
    3. Ben M. Harvey & Serge O. Dumoulin, 2017. "A network of topographic numerosity maps in human association cortex," Nature Human Behaviour, Nature, vol. 1(2), pages 1-9, February.
    4. Charley M Wu & Eric Schulz & Mona M Garvert & Björn Meder & Nicolas W Schuck, 2020. "Similarities and differences in spatial and non-spatial cognitive maps," PLOS Computational Biology, Public Library of Science, vol. 16(9), pages 1-28, September.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Jacob M. Paul & Martijn Ackooij & Tuomas C. Cate & Ben M. Harvey, 2022. "Numerosity tuning in human association cortices and local image contrast representations in early visual cortex," Nature Communications, Nature, vol. 13(1), pages 1-15, December.
    2. Magda Dubois & Tobias U. Hauser, 2022. "Value-free random exploration is linked to impulsivity," Nature Communications, Nature, vol. 13(1), pages 1-17, December.
    3. Amir Dezfouli & Bernard W Balleine, 2019. "Learning the structure of the world: The adaptive nature of state-space and action representations in multi-stage decision-making," PLOS Computational Biology, Public Library of Science, vol. 15(9), pages 1-22, September.
    4. Anna P. Giron & Simon Ciranka & Eric Schulz & Wouter Bos & Azzurra Ruggeri & Björn Meder & Charley M. Wu, 2023. "Developmental changes in exploration resemble stochastic optimization," Nature Human Behaviour, Nature, vol. 7(11), pages 1955-1967, November.
    5. Elisa Castaldi & Antonella Pomè & Guido Marco Cicchini & David Burr & Paola Binda, 2021. "The pupil responds spontaneously to perceived numerosity," Nature Communications, Nature, vol. 12(1), pages 1-8, December.
    6. Sébastien Czajko & Alexandre Vignaud & Evelyn Eger, 2024. "Human brain representations of internally generated outcomes of approximate calculation revealed by ultra-high-field brain imaging," Nature Communications, Nature, vol. 15(1), pages 1-12, December.
    7. Evi Hendrikx & Jacob M. Paul & Martijn Ackooij & Nathan Stoep & Ben M. Harvey, 2022. "Visual timing-tuned responses in human association cortices and response dynamics in early visual cortex," Nature Communications, Nature, vol. 13(1), pages 1-19, December.
    8. Maximilian E. Kirschhock & Andreas Nieder, 2022. "Number selective sensorimotor neurons in the crow translate perceived numerosity into number of actions," Nature Communications, Nature, vol. 13(1), pages 1-14, December.
    9. R Becket Ebitz & Brianna J Sleezer & Hank P Jedema & Charles W Bradberry & Benjamin Y Hayden, 2019. "Tonic exploration governs both flexibility and lapses," PLOS Computational Biology, Public Library of Science, vol. 15(11), pages 1-37, November.
    10. Farid Anvari & Stephan Billinger & Pantelis P. Analytis & Vithor Rosa Franco & Davide Marchiori, 2024. "Testing the convergent validity, domain generality, and temporal stability of selected measures of people’s tendency to explore," Nature Communications, Nature, vol. 15(1), pages 1-23, December.
    11. Lucas Lehnert & Michael L Littman & Michael J Frank, 2020. "Reward-predictive representations generalize across tasks in reinforcement learning," PLOS Computational Biology, Public Library of Science, vol. 16(10), pages 1-27, October.
    12. Shiva Farashahi & Alireza Soltani, 2021. "Computational mechanisms of distributed value representations and mixed learning strategies," Nature Communications, Nature, vol. 12(1), pages 1-18, December.

    More about this item

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:plo:pcbi00:1009092. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: ploscompbiol (email available below). General contact details of provider: https://journals.plos.org/ploscompbiol/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.