Advertisement

Unsupervised One-Shot Learning of Both Specific Instances and Generalised Classes with a Hippocampal Architecture

  • Gideon KowadloEmail author
  • Abdelrahman Ahmed
  • David Rawlinson
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12576)

Abstract

Established experimental procedures for one-shot machine learning do not test the ability to learn or remember specific instances of classes, a key feature of animal intelligence. Distinguishing specific instances is necessary for many real-world tasks, such as remembering which cup belongs to you. Generalisation within classes conflicts with the ability to separate instances of classes, making it difficult to achieve both capabilities within a single architecture. We propose an extension to the standard Omniglot classification-generalisation framework that additionally tests the ability to distinguish specific instances after one exposure and introduces noise and occlusion corruption. Learning is defined as an ability to classify as well as recall training samples. Complementary Learning Systems (CLS) is a popular model of mammalian brain regions believed to play a crucial role in learning from a single exposure to a stimulus. We created an artificial neural network implementation of CLS and applied it to the extended Omniglot benchmark. Our unsupervised model demonstrates comparable performance to existing supervised ANNs on the Omniglot classification task (requiring generalisation), without the need for domain-specific inductive biases. On the extended Omniglot instance-recognition task, the same model also demonstrates significantly better performance than a baseline nearest-neighbour approach, given partial occlusion and noise.

Keywords

CLS Hippocampus One-shot Specifics Instances Unsupervised Generalization. 

Notes

Acknowledgment

Thanks to Elkhonon Goldberg for enriching discussions on the hippocampal region and to Rotem Aharon for insights and analysis of Hopfield networks.

References

  1. 1.
    Ahmad, S., Scheinkman, L.: How can we be so dense? The benefits of using highly sparse representations. arXiv preprint arXiv:1903.11257 (2019)
  2. 2.
    George, D., et al.: A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs. Science, 1–19 (2017)Google Scholar
  3. 3.
    Gidaris, S., Bursuc, A., Komodakis, N., Pérez, P., Cord, M.: Boosting few-shot visual learning with self-supervision. In: Proceedings of the IEEE International Conference on Computer Vision (2019)Google Scholar
  4. 4.
    Greene, P., Howard, M., Bhattacharyya, R., Fellous, J.M.: Hippocampal anatomy supports the use of context in object recognition: a computational model. Comput. Intell. Neurosci. 2013 (2013)Google Scholar
  5. 5.
    Hewitt, L.B., Nye, M.I., Gane, A., Jaakkola, T., Tenenbaum, J.B.: The variational homoencoder: learning to learn high capacity generative models from few examples. arXiv preprint arXiv:1807.08919, July 2018
  6. 6.
    Hopfield, J.J.: Neural networks and physical systems with emergent collective computational abilities. Proc. Nat. Acad. Sci. 79(8) (1982)Google Scholar
  7. 7.
    Ketz, N., Morkonda, S.G., O’Reilly, R.C.: Theta coordinated error-driven learning in the hippocampus. PLoS Comput. Biol. 9(6) (2013)Google Scholar
  8. 8.
    Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: Proceedings of the 32nd International Conference on Machine Learning (2015)Google Scholar
  9. 9.
    Kowadlo, G., Ahmed, A., Rawlinson, D.: AHA! an ‘Artificial Hippocampal Algorithm’ for episodic machine learning. arXiv preprint arxiv:1909.10340 (2019)
  10. 10.
    Kumaran, D., Hassabis, D., McClelland, J.L.: What learning systems do intelligent agents need? Complementary learning systems theory updated. Trends Cogn. Sci. 20(7), 512–534 (2016)Google Scholar
  11. 11.
    Lake, B.M., Salakhutdinov, R., Gross, J., Tenenbaum, J.B.: One shot learning of simple visual concepts. In Proceedings of the 33rd Annual Conference of the Cognitive Science Society (2011)Google Scholar
  12. 12.
    Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)MathSciNetCrossRefGoogle Scholar
  13. 13.
    Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: The Omniglot challenge: a 3-year progress report. Curr. Opin. Behav. Sci. 29, 97–104 (2019)CrossRefGoogle Scholar
  14. 14.
    Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40(2012), 1–58 (2017)Google Scholar
  15. 15.
    Li, F.F., Fergus, R., Perona, P.: A Bayesian approach to unsupervised one-shot learning of object categories. In: Proceedings Ninth IEEE International Conference on Computer Vision (2003)Google Scholar
  16. 16.
    Li, F.F., Fergus, R., Perona, P.: One-shot learning of object categories. IEEE Trans. Pattern Anal. Mach. Intell. (2006)Google Scholar
  17. 17.
    Makhzani, A., Frey, B.: K-sparse autoencoders. arXiv preprint arXiv:1312.5663 (2013)
  18. 18.
    Makhzani, A., Frey, B.J.: Winner-take-all autoencoders. In: Advances in Neural Information Processing Systems, pp. 2791–2799 (2015)Google Scholar
  19. 19.
    McClelland, J.L., McNaughton, B.L., O’Reilly, R.C.: Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychol. Rev. 102(3), 419–457 (1995)CrossRefGoogle Scholar
  20. 20.
    Norman, K.A., O’Reilly, R.C.: Modeling hippocampal and neocortical contributions to recognition memory: a complementary-learning-systems approach. Psychol. Rev. 110(4), 611–646 (2003)CrossRefGoogle Scholar
  21. 21.
    O’Reilly, R.C., Bhattacharyya, R., Howard, M.D., Ketz, N.: Complementary learning systems. Cogn. Sci. 38(6), 1229–1248 (2014)CrossRefGoogle Scholar
  22. 22.
    Rolls, E.T.: A model of the operation of the hippocampus and entorhinal cortex in memory. Int. J. Neural Syst. 6 (1995)Google Scholar
  23. 23.
    Rolls, E.T.: The mechanisms for pattern completion and pattern separation in the hippocampus. Front. Syst. Neurosci. 7(October), 1–21 (2013)Google Scholar
  24. 24.
    Russell, S.J., Norvig, P.: Artificial Intelligence: A Modern Approach. Prentice Hall, Upper Saddle River (2009)Google Scholar
  25. 25.
    Schapiro, A.C., Turk-Browne, N.B., Botvinick, M.M., Norman, K.A.: Complementary learning systems within the hippocampus: a neural network modelling approach to reconciling episodic memory with statistical learning. Philos. Trans. Roy. Soc. B Biol. Sci. 372(1711), 20160049 (2017)CrossRefGoogle Scholar
  26. 26.
    Snell, J., Swersky, K., Zemel, R.S.: Prototypical networks for few-shot learning. In: Advances in Neural Information Processing Systems, pp. 4077–4087 (2017)Google Scholar
  27. 27.
    Vinyals, O., Blundell, C., Lillicrap, T., Kavukcuoglu, K.: Matching networks for one shot learning. In: Advances in Neural Information Processing Systems (2016)Google Scholar
  28. 28.
    Young, R.A.: The Gaussian derivative model for spatial vision: I. Retinal mechanisms. Spat. Vis. 2(4), 273–293 (1987)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.CerenautMelbourneAustralia

Personalised recommendations