Skip to main content

2017 | OriginalPaper | Buchkapitel

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

verfasst von : Benno Lüders, Mikkel Schläger, Aleksandra Korach, Sebastian Risi

Erschienen in: Applications of Evolutionary Computation

Verlag: Springer International Publishing

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

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.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat 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)CrossRef 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)CrossRef
2.
Zurück zum Zitat 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) 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.
Zurück zum Zitat Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Proceedings of the Advances in Neural Information Processing Systems 2 (1989) Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Proceedings of the Advances in Neural Information Processing Systems 2 (1989)
4.
Zurück zum Zitat 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) 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.
Zurück zum Zitat Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evol. Intell. 1(1), 47–62 (2008)CrossRef Floreano, D., Dürr, P., Mattiussi, C.: Neuroevolution: from architectures to learning. Evol. Intell. 1(1), 47–62 (2008)CrossRef
6.
Zurück zum Zitat Yao, X.: Evolving artificial neural networks. Proc. IEEE 87(9), 1423–1447 (1999)CrossRef Yao, X.: Evolving artificial neural networks. Proc. IEEE 87(9), 1423–1447 (1999)CrossRef
7.
Zurück zum Zitat 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) 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)
8.
Zurück zum Zitat 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) 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)
9.
Zurück zum Zitat Floreano, D., Urzelai, J.: Evolutionary robots with on-line self-organization and behavioral fitness. Neural Netw. 13(4), 431–443 (2000)CrossRef Floreano, D., Urzelai, J.: Evolutionary robots with on-line self-organization and behavioral fitness. Neural Netw. 13(4), 431–443 (2000)CrossRef
10.
Zurück zum Zitat 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_54CrossRef 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_​54CrossRef
11.
Zurück zum Zitat 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)CrossRef 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)CrossRef
12.
Zurück zum Zitat 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_50CrossRef 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_​50CrossRef
13.
Zurück zum Zitat 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)CrossRef 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)CrossRef
14.
Zurück zum Zitat 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) 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)
15.
Zurück zum Zitat 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) 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)
16.
Zurück zum Zitat 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) 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)
17.
Zurück zum Zitat 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) 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)
18.
Zurück zum Zitat Hebb, D.O.: The Organization of Behavior. Wiley & Sons, New York (1949) Hebb, D.O.: The Organization of Behavior. Wiley & Sons, New York (1949)
19.
Zurück zum Zitat 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) 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)
21.
Zurück zum Zitat 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) 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)
23.
Zurück zum Zitat 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)CrossRef 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)CrossRef
24.
Zurück zum Zitat Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)CrossRef Stanley, K.O., Miikkulainen, R.: Evolving neural networks through augmenting topologies. Evol. Comput. 10(2), 99–127 (2002)CrossRef
25.
Zurück zum Zitat 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)CrossRef 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)CrossRef
Metadaten
Titel
Continual and One-Shot Learning Through Neural Networks with Dynamic External Memory
verfasst von
Benno Lüders
Mikkel Schläger
Aleksandra Korach
Sebastian Risi
Copyright-Jahr
2017
DOI
https://doi.org/10.1007/978-3-319-55849-3_57

Premium Partner