2018

Emergence of grid-like representations by training recurrent neural networks to perform spatial localization

Cueva, Christopher J., Wei, Xue-Xin

Understand

Decades of research on the neural code underlying spatial navigation have revealed a diverse set of neural response properties.

The Entorhinal Cortex (EC) of the mammalian brain contains a rich set of spatial correlates, including grid cells which encode space using tessellating patterns.
However, the mechanisms and functional significance of these spatial representations remain largely mysterious.
As a new way to understand these neural representations, we trained recurrent neural networks (RNNs) to perform navigation tasks in 2D arenas based on velocity inputs.

Built on

Possible principles underlying the transformation of sensory messages
Horace B Barlow · 1961
Earlier work this paper cites.
Receptive fields, binocular interaction and functional architecture in the cat’s visual cortex
David H Hubel and Torsten N Wiesel · 1962
Earlier work this paper cites.
Place units in the hippocampus of the freely moving rat
John O’Keefe · 1976
Earlier work this paper cites.
Homing by path integration in a mammal
M-L Mittelstaedt and H Mittelstaedt · 1980
Earlier work this paper cites.
Emergence of simple-cell receptive field properties by learning a sparse code for natural images
Bruno A Olshausen and David J Field · 1996
Earlier work this paper cites.
Long short-term memory
Sepp Hochreiter and Jürgen Schmidhuber · 1997
Earlier work this paper cites.
Path integration and cognitive mapping in a continuous attractor neural network model
Alexei Samsonovich and Bruce L McNaughton · 1997
Earlier work this paper cites.
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio, and Patrick Haffner · 1998
Earlier work this paper cites.
Characterizing the sparseness of neural codes
B Willmore and DJ Tolhurst · 2001
Earlier work this paper cites.
Path integration in mammals
Ariane S Etienne and Kathryn J Jeffery · 2004
Earlier work this paper cites.
Spatial representation in the entorhinal cortex
Marianne Fyhn, Sturla Molden, Menno P Witter, Edvard I Moser, and May-Britt Moser · 2004
Earlier work this paper cites.
Microstructure of a spatial map in the entorhinal cortex
Torkel Hafting, Marianne Fyhn, Sturla Molden, May-Britt Moser, and Edvard I Moser · 2005
Earlier work this paper cites.
Path integration and the neural basis of the ’cognitive map’
Bruce L McNaughton, Francesco P Battaglia, Ole Jensen, Edvard I Moser, and May-Britt Moser · 2006
Earlier work this paper cites.
Conjunctive representation of position, direction, and velocity in entorhinal cortex
Francesca Sargolini, Marianne Fyhn, Torkel Hafting, Bruce L McNaughton, Menno P Witter, May-Britt Moser, and Edvard I Moser · 2006
Earlier work this paper cites.
Grid cells in mice
Marianne Fyhn, Torkel Hafting, Menno P Witter, Edvard I Moser, and May-Britt Moser · 2008
Earlier work this paper cites.
Visualizing data using t-sne
Laurens van der Maaten and Geoffrey Hinton · 2008
Earlier work this paper cites.
Place cells, grid cells, and the brain’s spatial representation system
Edvard I Moser, Emilio Kropff, and May-Britt Moser · 2008
Earlier work this paper cites.
Influence of boundary removal on the spatial representations of the medial entorhinal cortex
Francesco Savelli, D Yoganarasimha, and James J Knierim · 2008
Earlier work this paper cites.
Representation of geometric borders in the entorhinal cortex
Trygve Solstad, Charlotte N Boccara, Emilio Kropff, May-Britt Moser, and Edvard I Moser · 2008
Earlier work this paper cites.
Accurate path integration in continuous attractor network models of grid cells
Yoram Burak and Ila R Fiete · 2009
Earlier work this paper cites.

Similar

Boundary vector cells in the subiculum of the hippocampal formation
Colin Lever, Stephen Burton, Ali Jeewajee, John O’Keefe, and Neil Burgess · 2009
Cited alongside, same era.
Development of the spatial representation system in the rat
Rosamund F Langston, James A Ainge, Jonathan J Couey, Cathrin B Canto, Tale L Bjerknes, Menno P Witter, Edvard I Moser, and May-Britt Moser · 2010
Cited alongside, same era.
Development of the hippocampal cognitive map in preweanling rats
Tom J Wills, Francesca Cacucci, Neil Burgess, and John O’keefe · 2010
Cited alongside, same era.
Learning recurrent neural networks with hessian-free optimization
James Martens and Ilya Sutskever · 2011
Cited alongside, same era.
Grid cells without theta oscillations in the entorhinal cortex of bats
Michael M Yartsev, Menno P Witter, and Nachum Ulanovsky · 2011
Cited alongside, same era.
A map of visual space in the primate entorhinal cortex
Nathaniel J Killian, Michael J Jutras, and Elizabeth A Buffalo · 2012
Cited alongside, same era.
Imagenet classification with deep convolutional neural networks
Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton · 2012
Cited alongside, same era.
Neural representations of location composed of spatially periodic bands
Julija Krupic, Neil Burgess, and John O?Keefe · 2012
Cited alongside, same era.
The entorhinal grid map is discretized
Hanne Stensola, Tor Stensola, Trygve Solstad, Kristian Frøland, May-Britt Moser, and Edvard I Moser · 2012
Cited alongside, same era.
Representation learning: A review and new perspectives
Yoshua Bengio, Aaron Courville, and Pascal Vincent · 2013
Cited alongside, same era.
Recurrent inhibitory circuitry as a mechanism for grid formation
Jonathan J Couey, Aree Witoelar, Sheng-Jia Zhang, Kang Zheng, Jing Ye, Benjamin Dunn, Rafal Czajkowski, May-Britt Moser, Edvard I Moser, Yasser Roudi, et al · 2013
Cited alongside, same era.
Speech recognition with deep recurrent neural networks
Alex Graves, Abdel-Rahman Mohamed, and Geoffrey Hinton · 2013
Cited alongside, same era.

Then

Speed cells in the medial entorhinal cortex
Emilio Kropff, James E Carmichael, May-Britt Moser, and Edvard I Moser · 2015
Later among the works it cites.
Deep learning
Yann LeCun, Yoshua Bengio, and Geoffrey Hinton · 2015
Later among the works it cites.
Human-level control through deep reinforcement learning
Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Andrei A Rusu, Joel Veness, Marc G Bellemare, Alex Graves, Martin Riedmiller, Andreas K Fidjeland, Georg Ostrovski, et al · 2015
Later among the works it cites.
A neural network that finds a naturalistic solution for the production of muscle activity
David Sussillo, Mark M Churchland, Matthew T Kaufman, and Krishna V Shenoy · 2015
Later among the works it cites.
Generative image modeling using spatial lstms
Lucas Theis and Matthias Bethge · 2015
Later among the works it cites.
A principle of economy predicts the functional architecture of grid cells
Xue-Xin Wei, Jason Prentice, and Vijay Balasubramanian · 2015
Later among the works it cites.
Extracting grid cell characteristics from place cell inputs using non-negative principal component analysis
Yedidyah Dordek, Daniel Soudry, Ron Meir, and Dori Derdikman · 2016
Later among the works it cites.
Multiple running speed signals in medial entorhinal cortex
James R Hinman, Mark P Brandon, Jason R Climer, G William Chapman, and Michael E Hasselmo · 2016
Later among the works it cites.
Training recurrent networks to generate hypotheses about how the brain solves hard navigation problems
Original
Ingmar Kanitscheider and Ila Fiete · 2016
Later among the works it cites.
Random synaptic feedback weights support error backpropagation for deep learning
Timothy P Lillicrap, Daniel Cownden, Douglas B Tweed, and Colin J Akerman · 2016
Later among the works it cites.
Pixel recurrent neural networks
Original
Aaron van den Oord, Nal Kalchbrenner, and Koray Kavukcuoglu · 2016
Later among the works it cites.
Training excitatory-inhibitory recurrent neural networks for cognitive tasks: A simple and flexible framework
H Francis Song, Guangyu R Yang, and Xiao-Jing Wang · 2016
Later among the works it cites.
The hippocampus as a predictive map
Kimberly Lauren Stachenfeld, Matthew M Botvinick, and Samuel J Gershman · 2016
Later among the works it cites.
Using goal-driven deep learning models to understand sensory cortex
Daniel LK Yamins and James J DiCarlo · 2016
Later among the works it cites.
Mapping of a non-spatial dimension by the hippocampal–entorhinal circuit
Dmitriy Aronov, Rhino Nevers, and David W Tank · 2017
Later among the works it cites.
Grid and nongrid cells in medial entorhinal cortex represent spatial location and environmental features with complementary coding schemes
Geoffrey W Diehl, Olivia J Hon, Stefan Leutgeb, and Jill K Leutgeb · 2017
Later among the works it cites.
Towards deep learning with segregated dendrites
Jordan Guerguiev, Timothy P Lillicrap, and Blake A Richards · 2017
Later among the works it cites.
Deep neural networks in computational neuroscience
Tim Christian Kietzmann, Patrick McClure, and Nikolaus Kriegeskorte · 2017
Later among the works it cites.
Biologically plausible learning in recurrent neural networks reproduces neural dynamics observed during cognitive tasks
Thomas Miconi · 2017
Later among the works it cites.
A mechanism for self-organized error-correction of grid cells by border cells
Eli Pollock, Niral Desai, Xue-Xin Wei, and Vijay B Balasubramanian · 2017
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…