Skip to main content

Investigating Efficient Learning and Compositionality in Generative LSTM Networks

Part of the Lecture Notes in Computer Science book series (LNTCS,volume 12396)

Abstract

When comparing human with artificial intelligence, one major difference is apparent: Humans can generalize very broadly from sparse data sets because they are able to recombine and reintegrate data components in compositional manners. To investigate differences in efficient learning, Joshua B. Tenenbaum and colleagues developed the character challenge: First an algorithm is trained in generating handwritten characters. In a next step, one version of a new type of character is presented. An efficient learning algorithm is expected to be able to re-generate this new character, to identify similar versions of this character, to generate new variants of it, and to create completely new character types. In the past, the character challenge was only met by complex algorithms that were provided with stochastic primitives. Here, we tackle the challenge without providing primitives. We apply a minimal recurrent neural network (RNN) model with one feedforward layer and one LSTM layer and train it to generate sequential handwritten character trajectories from one-hot encoded inputs. To manage the re-generation of untrained characters when presented with only one example of them, we introduce a one-shot inference mechanism: the gradient signal is backpropagated to the feedforward layer weights only, leaving the LSTM layer untouched. We show that our model is able to meet the character challenge by recombining previously learned dynamic substructures, which are visible in the hidden LSTM states. Making use of the compositional abilities of RNNs in this way might be an important step towards bridging the gap between human and artificial intelligence.

Keywords

  • Generative RNN
  • LSTMs
  • Efficient learning
  • Compositionality
  • Character challenge

This is a preview of subscription content, access via your institution.

Buying options

Chapter
USD   29.95
Price excludes VAT (USA)
  • DOI: 10.1007/978-3-030-61609-0_12
  • Chapter length: 12 pages
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
eBook
USD   119.00
Price excludes VAT (USA)
  • ISBN: 978-3-030-61609-0
  • Instant PDF download
  • Readable on all devices
  • Own it forever
  • Exclusive offer for individuals only
  • Tax calculation will be finalised during checkout
Softcover Book
USD   159.99
Price excludes VAT (USA)
Fig. 1.
Fig. 2.
Fig. 3.
Fig. 4.
Fig. 5.
Fig. 6.
Fig. 7.

References

  1. Battaglia, P.W., et al.: Relational inductive biases, deep learning, and graph networks. arXiv preprint arXiv:1806.01261 (2018)

  2. Geirhos, R., Temme, C.R.M., Rauber, J., Schütt, H.H., Bethge, M., Wichmann, F.A.: Generalisation in humans and deep neural networks. In: Advances in Neural Information Processing Systems (NeurIPS), pp. 7538–7550. Curran Associates, Inc. (2018)

    Google Scholar 

  3. Hassabis, D., Kumaran, D., Summerfield, C., Botvinick, M.: Neuroscience-inspired artificial intelligence. Neuron 95(2), 245–258 (2017)

    CrossRef  Google Scholar 

  4. Hofstadter, D.: Metamagical Themas: Questing for the Essence of Mind and Pattern. Basic Books, New York (1985)

    Google Scholar 

  5. Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. In: 3rd International Conference for Learning Representations (2015)

    Google Scholar 

  6. Lake, B., Baroni, M.: Still not systematic after all these years: On the compositional skills of sequence-to-sequence recurrent networks. arXiv preprint arXiv:1711.00350 (2018)

  7. Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: Human-level concept learning through probabilistic program induction. Science 350(6266), 1332–1338 (2015)

    MathSciNet  CrossRef  Google Scholar 

  8. Lake, B.M., Salakhutdinov, R., Tenenbaum, J.B.: The Omniglot challenge: a 3-year progress report. Curr. Opin. Behav. Sci. 29, 97–104 (2019)

    CrossRef  Google Scholar 

  9. Lake, B.M., Ullman, T.D., Tenenbaum, J.B., Gershman, S.J.: Building machines that learn and think like people. Behav. Brain Sci. 40, e253 (2017)

    CrossRef  Google Scholar 

  10. LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)

    CrossRef  Google Scholar 

  11. Marcus, G.: Deep learning: A critical appraisal. arXiv preprint arXiv:1801.00631 (2018)

  12. Nguyen, A., Yosinski, J., Clune, J.: Deep neural networks are easily fooled: high confidence predictions for unrecognizable images. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 427–436 (2015)

    Google Scholar 

  13. Otte, S., Rubisch, P., Butz, M.V.: Gradient-based learning of compositional dynamics with modular RNNs. In: Tetko, I.V., Kurková, V., Karpov, P., Theis, F. (eds.) ICANN 2019. LNCS, vol. 11727, pp. 484–496. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-30487-4_38

    CrossRef  Google Scholar 

  14. Werbos, P.J.: Backpropagation through time: what it does and how to do it. In: Proceedings of the IEEE, pp. 1550–1560 (1990)

    Google Scholar 

Download references

Acknowledgements

The results of this work were produced with the help of the GPU cluster of the BMBF funded project Training Center for Machine Learning (TCML) at the Eberhard Karls Universität Tübingen, administered by the Cognitive Systems group. We especially thank Maximus Mutschler who is responsible for the maintenance of the cluster.

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Sarah Fabi .

Editor information

Editors and Affiliations

Rights and permissions

Reprints and Permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Verify currency and authenticity via CrossMark

Cite this paper

Fabi, S., Otte, S., Wiese, J.G., Butz, M.V. (2020). Investigating Efficient Learning and Compositionality in Generative LSTM Networks. In: Farkaš, I., Masulli, P., Wermter, S. (eds) Artificial Neural Networks and Machine Learning – ICANN 2020. ICANN 2020. Lecture Notes in Computer Science(), vol 12396. Springer, Cham. https://doi.org/10.1007/978-3-030-61609-0_12

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-61609-0_12

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-61608-3

  • Online ISBN: 978-3-030-61609-0

  • eBook Packages: Computer ScienceComputer Science (R0)