Continual and One-Shot Learning Through Neural Networks with Dynamic External Memory

  • Benno Lüders
  • Mikkel Schläger
  • Aleksandra Korach
  • Sebastian Risi
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 10199)

Abstract

Training neural networks to quickly learn new skills without forgetting previously learned skills is an important open challenge in machine learning. A common problem for adaptive networks that can learn during their lifetime is that the weights encoding a particular task are often overridden when a new task is learned. This paper takes a step in overcoming this limitation by building on the recently proposed Evolving Neural Turing Machine (ENTM) approach. In the ENTM, neural networks are augmented with an external memory component that they can write to and read from, which allows them to store associations quickly and over long periods of time. The results in this paper demonstrate that the ENTM is able to perform one-shot learning in reinforcement learning tasks without catastrophic forgetting of previously stored associations. Additionally, we introduce a new ENTM default jump mechanism that makes it easier to find unused memory location and therefor facilitates the evolution of continual learning networks. Our results suggest that augmenting evolving networks with an external memory component is not only a viable mechanism for adaptive behaviors in neuroevolution but also allows these networks to perform continual and one-shot learning at the same time.

Keywords

Neural Turing Machine Continual learning Adaptive neural networks Plasticity Memory Neuroevolution 

Notes

Acknowledgment

Computation/simulation for the work described in this paper was supported by the DeIC National HPC Centre, SDU.

References

  1. 1.
    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)CrossRefGoogle Scholar
  2. 2.
    Rusu, A.A., Rabinowitz, N.C., Desjardins, G., Soyer, H., Kirkpatrick, J., Kavukcuoglu, K., Pascanu, R., Hadsell, R.: Progressive neural networks. Preprint arXiv:1606.04671 (2016)
  3. 3.
    Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Proceedings of the Advances in Neural Information Processing Systems 2 (1989)Google Scholar
  4. 4.
    Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A.A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al.: Overcoming catastrophic forgetting in neural networks. arXiv preprint arXiv:1612.00796 (2016)
  5. 5.
    Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evol. Intell. 1(1), 47–62 (2008)CrossRefGoogle Scholar
  6. 6.
    Yao, X.: Evolving artificial neural networks. Proc. IEEE 87(9), 1423–1447 (1999)CrossRefGoogle Scholar
  7. 7.
    Risi, S., Togelius, J.: Neuroevolution in games: state of the art and open challenges. IEEE Trans. Comput. Intell. AI Games PP(99), 1–1 (2015)Google Scholar
  8. 8.
    Stanley, K.O., Bryant, B.D., Miikkulainen, R.: Evolving adaptive neural networks with and without adaptive synapses. In: The 2003 Congress on Evolutionary Computation, CEC 2003, vol. 4, pp. 2557–2564. IEEE (2003)Google Scholar
  9. 9.
    Floreano, D., Urzelai, J.: Evolutionary robots with on-line self-organization and behavioral fitness. Neural Netw. 13(4), 431–443 (2000)CrossRefGoogle Scholar
  10. 10.
    Blynel, J., Floreano, D.: Exploring the T-Maze: evolving learning-like robot behaviors using CTRNNs. In: Cagnoni, S., Johnson, C.G., Cardalda, J.J.R., Marchiori, E., Corne, D.W., Meyer, J.-A., Gottlieb, J., Middendorf, M., Guillot, A., Raidl, G.R., Hart, E. (eds.) EvoWorkshops 2003. LNCS, vol. 2611, pp. 593–604. Springer, Heidelberg (2003). doi: 10.1007/3-540-36605-9_54CrossRefGoogle Scholar
  11. 11.
    Ellefsen, K.O., Mouret, J.B., Clune, J.: Neural modularity helps organisms evolve to learn new skills without forgetting old skills. PLoS Comput. Biol. 11(4), e1004128 (2015)CrossRefGoogle Scholar
  12. 12.
    Risi, S., Stanley, K.O.: Indirectly encoding neural plasticity as a pattern of local rules. In: Doncieux, S., Girard, B., Guillot, A., Hallam, J., Meyer, J.-A., Mouret, J.-B. (eds.) SAB 2010. LNCS (LNAI), vol. 6226, pp. 533–543. Springer, Heidelberg (2010). doi: 10.1007/978-3-642-15193-4_50CrossRefGoogle Scholar
  13. 13.
    Silva, F., Urbano, P., Correia, L., Christensen, A.L.: odNEAT: an algorithm for decentralised online evolution of robotic controllers. Evol. Comput. 23(3), 421–449 (2015)CrossRefGoogle Scholar
  14. 14.
    Soltoggio, A., Bullinaria, J.A., Mattiussi, C.: Drr, P., Floreano, D.: Evolutionary advantages of neuromodulated plasticity in dynamic, reward-based scenarios. In: Bullock, S., Noble, J., Watson, R., Bedau, M.A., (eds.): Proceedings of the 11th International Conference on Artificial Life (Alife XI), pp. 569–576. MIT Press, Cambridge (2008)Google Scholar
  15. 15.
    Risi, S., Stanley, K.O.: A unified approach to evolving plasticity and neural geometry. In: The 2012 International Joint Conference on Neural Networks (IJCNN), pp. 1–8. IEEE (2012)Google Scholar
  16. 16.
    Norouzzadeh, M.S., Clune, J.: Neuromodulation improves the evolution of forward models. In: Proceedings of the Genetic and Evolutionary Computation Conference 2016, GECCO 2016, pp. 157–164. ACM, New York (2016)Google Scholar
  17. 17.
    Löwe, M., Risi, S.: Accelerating the evolution of cognitive behaviors through human-computer collaboration. In: Proceedings of the Genetic and Evolutionary Computation Conference 2016, GECCO 2016, pp. 133–140. ACM, New York (2016)Google Scholar
  18. 18.
    Hebb, D.O.: The Organization of Behavior. Wiley & Sons, New York (1949)Google Scholar
  19. 19.
    McCloskey, M., Cohen, N.: Catastrophic interference in connectionist networks: the sequential learning problem. In: Bower, G.H. (ed.) The Psychology of Learning and Motivation, vol. 24, pp. 109–164 (1989)Google Scholar
  20. 20.
    Graves, A., Wayne, G., Danihelka, I.: Neural turing machines. arXiv:1410.5401 (2014)
  21. 21.
    Greve, R.B., Jacobsen, E.J., Risi, S.: Evolving neural turing machines for reward-based learning. In: Proceedings of the Genetic and Evolutionary Computation Conference 2016, GECCO 2016, pp. 117–124. ACM, New York (2016)Google Scholar
  22. 22.
    Weston, J., Chopra, S., Bordes, A.: Memory networks. Preprint arXiv:1410.3916 (2014)
  23. 23.
    Graves, A., Wayne, G., Reynolds, M., Harley, T., Danihelka, I., Grabska-Barwińska, A., Colmenarejo, S.G., Grefenstette, E., Ramalho, T., Agapiou, J., et al.: Hybrid computing using a neural network with dynamic external memory. Nature 538(7626), 471–476 (2016)CrossRefGoogle Scholar
  24. 24.
    Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)CrossRefGoogle Scholar
  25. 25.
    Foster, D., Morris, R., Dayan, P., et al.: A model of hippocampally dependent navigation, using the temporal difference learning rule. Hippocampus 10(1), 1–16 (2000)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing AG 2017

Authors and Affiliations

  • Benno Lüders
    • 1
  • Mikkel Schläger
    • 1
  • Aleksandra Korach
    • 1
  • Sebastian Risi
    • 1
  1. 1.IT University of CopenhagenCopenhagenDenmark

Personalised recommendations