Hostname: page-component-cd9895bd7-8ctnn Total loading time: 0 Render date: 2024-12-26T19:47:25.306Z Has data issue: false hasContentIssue false
  • English
  • Français

Is coding a relevant metaphor for building AI?

Published online by Cambridge University Press:  28 November 2019

Adam Santoro ,
Felix Hill ,
David Barrett ,
David Raposo ,
Matt Botvinick  and
Timothy Lillicrap
Adam Santoro
Affiliation:
DeepMind, LondonN1C4AG, United Kingdom. [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] www.deepmind.com
Felix Hill
Affiliation:
DeepMind, LondonN1C4AG, United Kingdom. [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] www.deepmind.com
David Barrett
Affiliation:
DeepMind, LondonN1C4AG, United Kingdom. [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] www.deepmind.com
David Raposo
Affiliation:
DeepMind, LondonN1C4AG, United Kingdom. [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] www.deepmind.com
Matt Botvinick
Affiliation:
DeepMind, LondonN1C4AG, United Kingdom. [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] www.deepmind.com
Timothy Lillicrap
Affiliation:
DeepMind, LondonN1C4AG, United Kingdom. [email protected] [email protected] [email protected] [email protected] [email protected] [email protected] www.deepmind.com
Get access Rights & Permissions [Opens in a new window]

Abstract

Brette contends that the neural coding metaphor is an invalid basis for theories of what the brain does. Here, we argue that it is an insufficient guide for building an artificial intelligence that learns to accomplish short- and long-term goals in a complex, changing environment.

Type
Open Peer Commentary
Information
Behavioral and Brain Sciences , Volume 42 , 2019 , e240
Check for updates
Copyright
Copyright © Cambridge University Press 2019

Access options

Get access to the full version of this content by using one of the access options below. (Log in options will check for institutional or personal access. Content may require purchase if you do not have access.)

Footnotes

1.

AS and FH contributed equally to this work.

References

Banino, A., Barry, C., Uria, B., Blundell, C., Lillicrap, T., Mirowski, P., Pritzel, A., Chadwick, M. J., Degris, T., Modayil, J., Wayne, G., Soyer, H., Viola, F., Zhang, B., Goroshin, R., Rabinowitz, N., Pascanu, R., Beattie, C., Petersen, S., Sadik, A., Gaffney, S., King, H., Kavukcuoglu, K., Hassabis, D., Hadsell, R., Kumaran, D. & Wayne, G. (2018) Vector-based navigation using grid-like representations in artificial agents. Nature 557(7705):429–33.CrossRefGoogle ScholarPubMed
Barack, D. & Jaegle, A. (2019) The role of analysis-by-decomposition in neurocognitive modeling. arXiv preprint.Google Scholar
Brooks, R. A. (1991a) Intelligence without representation. Artificial Intelligence 47(1–3):139–59. doi:10.1016/0004-3702(91)90053-M.CrossRefGoogle Scholar
Cisek, P. (1999) Beyond the computer metaphor: Behaviour as interaction. Journal of Consciousness Studies 6(11/12):125–42.Google Scholar
Cueva, C. J. & Wei, X. X. (2018) Emergence of grid-like representations by training recurrent neural networks to perform spatial localization. arXiv preprint arXiv:1803.07770.Google Scholar
He, K., Zhang, X., Ren, S. & Sun, J. (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 770–78. IEEE.CrossRefGoogle Scholar
Krakauer, J. W., Ghazanfar, A. A., Gomez-Marin, A., MacIver, M. A. & Poeppel, D. (2017) Neuroscience needs behavior: Correcting a reductionist bias. Neuron 93(3):480–90.CrossRefGoogle ScholarPubMed
Marblestone, A. H., Wayne, G. & Kording, K. P. (2016) Toward an integration of deep learning and neuroscience. Frontiers in Computational Neuroscience 10:94.CrossRefGoogle ScholarPubMed
Russell, S. J. & Norvig, P. (2016) Artificial intelligence: A modern approach. Pearson Education Limited.Google Scholar
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., Van Den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., Dieleman, S., Grewe, D., Nham, J., Kalchbrenner, N., Sutskever, I., Lillicrap, T., Leach, M., Kavukcuoglu, K., Graepel, T. & Hassabis, D. (2016) Mastering the game of Go with deep neural networks and tree search. Nature 529(7587):484–9.CrossRefGoogle ScholarPubMed
Sutton, R. (2019) The bitter lesson. Available at: http://incompleteideas.net/IncIdeas/BitterLesson.html.Google Scholar
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L. & Polosukhin, I. (2017) Attention is all you need. In: Advances in neural information processing systems (NIPS 2017), ed. Guyon, I., Luxburg, U. V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S. & Garnett, R., pp. 5998–6008. Neural Information Processing Systems Foundation.Google Scholar