Crossing the Cleft: Communication Challenges Between Neuroscience and Artificial Intelligence
Abstract
Historically, neuroscience principles have heavily influenced artificial intelligence (AI), for example the influence of the perceptron model, essentially a simple model of a biological neuron, on artificial neural networks. More recently, notable recent AI advances, for example the growing popularity of reinforcement learning, often appear more aligned with cognitive neuroscience or psychology, focusing on function at a relatively abstract level. At the same time, neuroscience stands poised to enter a new era of large-scale high-resolution data and appears more focused on underlying neural mechanisms or architectures that can, at times, seem rather removed from functional descriptions. While this might seem to foretell a new generation of AI approaches arising from a deeper exploration of neuroscience specifically for AI, the most direct path for achieving this is unclear. Here we discuss cultural differences between the two fields, including divergent priorities that should be considered when leveraging modern-day neuroscience for AI. For example, the two fields feed two very different applications that at times require potentially conflicting perspectives. We highlight small but significant cultural shifts that we feel would greatly facilitate increased synergy between the two fields.
- Authors:
-
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Publication Date:
- Research Org.:
- Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
- Sponsoring Org.:
- USDOE National Nuclear Security Administration (NNSA); Intelligence Advanced Research Projects Activity (IARPA); Defense Advanced Research Projects Agency (DARPA); USDOE Laboratory Directed Research and Development (LDRD) Program
- OSTI Identifier:
- 1617318
- Report Number(s):
- SAND-2020-4146J
Journal ID: ISSN 1662-5188; 685384
- Grant/Contract Number:
- AC04-94AL85000; NA0003525
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Frontiers in Computational Neuroscience
- Additional Journal Information:
- Journal Volume: 14; Journal Issue: 39; Journal ID: ISSN 1662-5188
- Publisher:
- Frontiers Research Foundation
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 97 MATHEMATICS AND COMPUTING; 60 APPLIED LIFE SCIENCES; artificial intelligence; neural-inspired algorithms; neuromorphic; deep learning; artificial neural network
Citation Formats
Chance, Frances S., Aimone, James B., Musuvathy, Srideep S., Smith, Michael R., Vineyard, Craig M., and Wang, Felix. Crossing the Cleft: Communication Challenges Between Neuroscience and Artificial Intelligence. United States: N. p., 2020.
Web. doi:10.3389/fncom.2020.00039.
Chance, Frances S., Aimone, James B., Musuvathy, Srideep S., Smith, Michael R., Vineyard, Craig M., & Wang, Felix. Crossing the Cleft: Communication Challenges Between Neuroscience and Artificial Intelligence. United States. https://doi.org/10.3389/fncom.2020.00039
Chance, Frances S., Aimone, James B., Musuvathy, Srideep S., Smith, Michael R., Vineyard, Craig M., and Wang, Felix. Wed .
"Crossing the Cleft: Communication Challenges Between Neuroscience and Artificial Intelligence". United States. https://doi.org/10.3389/fncom.2020.00039. https://www.osti.gov/servlets/purl/1617318.
@article{osti_1617318,
title = {Crossing the Cleft: Communication Challenges Between Neuroscience and Artificial Intelligence},
author = {Chance, Frances S. and Aimone, James B. and Musuvathy, Srideep S. and Smith, Michael R. and Vineyard, Craig M. and Wang, Felix},
abstractNote = {Historically, neuroscience principles have heavily influenced artificial intelligence (AI), for example the influence of the perceptron model, essentially a simple model of a biological neuron, on artificial neural networks. More recently, notable recent AI advances, for example the growing popularity of reinforcement learning, often appear more aligned with cognitive neuroscience or psychology, focusing on function at a relatively abstract level. At the same time, neuroscience stands poised to enter a new era of large-scale high-resolution data and appears more focused on underlying neural mechanisms or architectures that can, at times, seem rather removed from functional descriptions. While this might seem to foretell a new generation of AI approaches arising from a deeper exploration of neuroscience specifically for AI, the most direct path for achieving this is unclear. Here we discuss cultural differences between the two fields, including divergent priorities that should be considered when leveraging modern-day neuroscience for AI. For example, the two fields feed two very different applications that at times require potentially conflicting perspectives. We highlight small but significant cultural shifts that we feel would greatly facilitate increased synergy between the two fields.},
doi = {10.3389/fncom.2020.00039},
journal = {Frontiers in Computational Neuroscience},
number = 39,
volume = 14,
place = {United States},
year = {Wed May 06 00:00:00 EDT 2020},
month = {Wed May 06 00:00:00 EDT 2020}
}
Web of Science
Works referenced in this record:
Deep convolutional models improve predictions of macaque V1 responses to natural images
journal, April 2019
- Cadena, Santiago A.; Denfield, George H.; Walker, Edgar Y.
- PLOS Computational Biology, Vol. 15, Issue 4
Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
journal, July 2015
- Guclu, U.; van Gerven, M. A. J.
- Journal of Neuroscience, Vol. 35, Issue 27
Navigating cognition: Spatial codes for human thinking
journal, November 2018
- Bellmund, Jacob L. S.; Gärdenfors, Peter; Moser, Edvard I.
- Science, Vol. 362, Issue 6415
Head-direction cells recorded from the postsubiculum in freely moving rats. II. Effects of environmental manipulations
journal, February 1990
- Taube, Js; Muller, Ru; Ranck, Jb
- The Journal of Neuroscience, Vol. 10, Issue 2
Performance-optimized hierarchical models predict neural responses in higher visual cortex
journal, May 2014
- Yamins, D. L. K.; Hong, H.; Cadieu, C. F.
- Proceedings of the National Academy of Sciences, Vol. 111, Issue 23
Probing Deep Brain Circuitry: New Advances in in Vivo Calcium Measurement Strategies
journal, December 2016
- Girven, Kasey S.; Sparta, Dennis R.
- ACS Chemical Neuroscience, Vol. 8, Issue 2
Engineering a Less Artificial Intelligence
journal, September 2019
- Sinz, Fabian H.; Pitkow, Xaq; Reimer, Jacob
- Neuron, Vol. 103, Issue 6
Sequencing the Connectome
journal, October 2012
- Zador, Anthony M.; Dubnau, Joshua; Oyibo, Hassana K.
- PLoS Biology, Vol. 10, Issue 10
A million spiking-neuron integrated circuit with a scalable communication network and interface
journal, August 2014
- Merolla, P. A.; Arthur, J. V.; Alvarez-Icaza, R.
- Science, Vol. 345, Issue 6197
Thalamic regulation of switching between cortical representations enables cognitive flexibility
journal, November 2018
- Rikhye, Rajeev V.; Gilra, Aditya; Halassa, Michael M.
- Nature Neuroscience, Vol. 21, Issue 12
Performance of an insect-inspired target tracker in natural conditions
journal, February 2017
- Bagheri, Zahra M.; Wiederman, Steven D.; Cazzolato, Benjamin S.
- Bioinspiration & Biomimetics, Vol. 12, Issue 2
A predictive focus of gain modulation encodes target trajectories in insect vision
journal, July 2017
- Wiederman, Steven D.; Fabian, Joseph M.; Dunbier, James R.
- eLife, Vol. 6
Genetic Approaches to Neural Circuits in the Mouse
journal, July 2013
- Josh Huang, Z.; Zeng, Hongkui
- Annual Review of Neuroscience, Vol. 36, Issue 1
Evolving Images for Visual Neurons Using a Deep Generative Network Reveals Coding Principles and Neuronal Preferences
journal, May 2019
- Ponce, Carlos R.; Xiao, Will; Schade, Peter F.
- Cell, Vol. 177, Issue 4
Selective Attention in an Insect Visual Neuron
journal, January 2013
- Wiederman, Steven D.; O’Carroll, David C.
- Current Biology, Vol. 23, Issue 2
An autonomous robot inspired by insect neurophysiology pursues moving features in natural environments
journal, July 2017
- Bagheri, Zahra M.; Cazzolato, Benjamin S.; Grainger, Steven
- Journal of Neural Engineering, Vol. 14, Issue 4
Neuroscience Needs Behavior: Correcting a Reductionist Bias
journal, February 2017
- Krakauer, John W.; Ghazanfar, Asif A.; Gomez-Marin, Alex
- Neuron, Vol. 93, Issue 3
Overcoming catastrophic forgetting in neural networks
journal, March 2017
- Kirkpatrick, James; Pascanu, Razvan; Rabinowitz, Neil
- Proceedings of the National Academy of Sciences, Vol. 114, Issue 13
A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
journal, December 2018
- Silver, David; Hubert, Thomas; Schrittwieser, Julian
- Science, Vol. 362, Issue 6419
Feature-based attention influences motion processing gain in macaque visual cortex
journal, June 1999
- Treue, Stefan; Trujillo, Julio C. Martínez
- Nature, Vol. 399, Issue 6736
Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
journal, January 1962
- Hubel, D. H.; Wiesel, T. N.
- The Journal of Physiology, Vol. 160, Issue 1
Neuromorphic Silicon Neuron Circuits
journal, January 2011
- Indiveri, Giacomo; Linares-Barranco, Bernabé; Hamilton, Tara Julia
- Frontiers in Neuroscience, Vol. 5
Alleviating catastrophic forgetting using context-dependent gating and synaptic stabilization
journal, October 2018
- Masse, Nicolas Y.; Grant, Gregory D.; Freedman, David J.
- Proceedings of the National Academy of Sciences, Vol. 115, Issue 44
Inception loops discover what excites neurons most using deep predictive models
journal, November 2019
- Walker, Edgar Y.; Sinz, Fabian H.; Cobos, Erick
- Nature Neuroscience, Vol. 22, Issue 12
Spatial Representation in the Entorhinal Cortex
journal, August 2004
- Fyhn, M.
- Science, Vol. 305, Issue 5688
Accurate Estimation of Neural Population Dynamics without Spike Sorting
journal, July 2019
- Trautmann, Eric M.; Stavisky, Sergey D.; Lahiri, Subhaneil
- Neuron, Vol. 103, Issue 2
A Canonical Microcircuit for Neocortex
journal, December 1989
- Douglas, Rodney J.; Martin, Kevan A. C.; Whitteridge, David
- Neural Computation, Vol. 1, Issue 4
A deep learning framework for neuroscience
journal, October 2019
- Richards, Blake A.; Lillicrap, Timothy P.; Beaudoin, Philippe
- Nature Neuroscience, Vol. 22, Issue 11
Visual information retrieval using synthesized imagery
conference, January 2007
- Thomee, Bart; Huiskes, Mark J.; Bakker, Erwin
- Proceedings of the 6th ACM international conference on Image and video retrieval - CIVR '07
Classification of electrophysiological and morphological neuron types in the mouse visual cortex
journal, June 2019
- Gouwens, Nathan W.; Sorensen, Staci A.; Berg, Jim
- Nature Neuroscience, Vol. 22, Issue 7
Principles of connectivity among morphologically defined cell types in adult neocortex
journal, November 2015
- Jiang, X.; Shen, S.; Cadwell, C. R.
- Science, Vol. 350, Issue 6264
Head-direction cells recorded from the postsubiculum in freely moving rats. I. Description and quantitative analysis
journal, February 1990
- Taube, Js; Muller, Ru; Ranck, Jb
- The Journal of Neuroscience, Vol. 10, Issue 2
Properties of neuronal facilitation that improve target tracking in natural pursuit simulations
journal, July 2015
- Bagheri, Zahra M.; Wiederman, Steven D.; Cazzolato, Benjamin S.
- Journal of The Royal Society Interface, Vol. 12, Issue 108
A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs
journal, October 2017
- George, Dileep; Lehrach, Wolfgang; Kansky, Ken
- Science, Vol. 358, Issue 6368
Spatial cognition and neuro-mimetic navigation: a model of hippocampal place cell activity
journal, August 2000
- Arleo, Angelo; Gerstner, Wulfram
- Biological Cybernetics, Vol. 83, Issue 3
Functional Imaging and Optogenetics in Drosophila
journal, April 2018
- Simpson, Julie H.; Looger, Loren L.
- Genetics, Vol. 208, Issue 4
How advances in neural recording affect data analysis
journal, January 2011
- Stevenson, Ian H.; Kording, Konrad P.
- Nature Neuroscience, Vol. 14, Issue 2
A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex
journal, January 2019
- Hawkins, Jeff; Lewis, Marcus; Klukas, Mirko
- Frontiers in Neural Circuits, Vol. 12
A Model for the Detection of Moving Targets in Visual Clutter Inspired by Insect Physiology
journal, July 2008
- Wiederman, Steven D.; Shoemaker, Patrick A.; O'Carroll, David C.
- PLoS ONE, Vol. 3, Issue 7
NeuroSLAM: a brain-inspired SLAM system for 3D environments
journal, September 2019
- Yu, Fangwen; Shang, Jianga; Hu, Youjian
- Biological Cybernetics, Vol. 113, Issue 5-6
A Complete Electron Microscopy Volume of the Brain of Adult Drosophila melanogaster
journal, July 2018
- Zheng, Zhihao; Lauritzen, J. Scott; Perlman, Eric
- Cell, Vol. 174, Issue 3
Effects of Attention on Orientation-Tuning Functions of Single Neurons in Macaque Cortical Area V4
journal, January 1999
- McAdams, Carrie J.; Maunsell, John H. R.
- The Journal of Neuroscience, Vol. 19, Issue 1
Training deep neural networks for binary communication with the Whetstone method
journal, January 2019
- Severa, William; Vineyard, Craig M.; Dellana, Ryan
- Nature Machine Intelligence, Vol. 1, Issue 2
Neural population control via deep image synthesis
journal, May 2019
- Bashivan, Pouya; Kar, Kohitij; DiCarlo, James J.
- Science, Vol. 364, Issue 6439
Neuroscience-Inspired Artificial Intelligence
journal, July 2017
- Hassabis, Demis; Kumaran, Dharshan; Summerfield, Christopher
- Neuron, Vol. 95, Issue 2
The neocortical circuit: themes and variations
journal, January 2015
- Harris, Kenneth D.; Shepherd, Gordon M. G.
- Nature Neuroscience, Vol. 18, Issue 2
High-precision automated reconstruction of neurons with flood-filling networks
journal, July 2018
- Januszewski, Michał; Kornfeld, Jörgen; Li, Peter H.
- Nature Methods, Vol. 15, Issue 8
The hippocampus as a spatial map. Preliminary evidence from unit activity in the freely-moving rat
journal, November 1971
- O'Keefe, J.; Dostrovsky, J.
- Brain Research, Vol. 34, Issue 1
Neural algorithms and computing beyond Moore's law
journal, March 2019
- Aimone, James B.
- Communications of the ACM, Vol. 62, Issue 4
A Survey on Transfer Learning
journal, October 2010
- Pan, Sinno Jialin; Yang, Qiang
- IEEE Transactions on Knowledge and Data Engineering, Vol. 22, Issue 10
Toward an Integration of Deep Learning and Neuroscience
journal, September 2016
- Marblestone, Adam H.; Wayne, Greg; Kording, Konrad P.
- Frontiers in Computational Neuroscience, Vol. 10
Gradient-based learning applied to document recognition
journal, January 1998
- Lecun, Y.; Bottou, L.; Bengio, Y.
- Proceedings of the IEEE, Vol. 86, Issue 11
Evidence that recurrent circuits are critical to the ventral stream’s execution of core object recognition behavior
journal, April 2019
- Kar, Kohitij; Kubilius, Jonas; Schmidt, Kailyn
- Nature Neuroscience, Vol. 22, Issue 6
A Self-organizing Method for Robot Navigation based on Learned Place and Head-Direction Cells
conference, July 2018
- Zhou, Xiaomao; Weber, Cornelius; Wermter, Stefan
- 2018 International Joint Conference on Neural Networks (IJCNN)
Deep learning in spiking neural networks
journal, March 2019
- Tavanaei, Amirhossein; Ghodrati, Masoud; Kheradpisheh, Saeed Reza
- Neural Networks, Vol. 111
Neurogenesis deep learning: Extending deep networks to accommodate new classes
conference, May 2017
- Draelos, Timothy J.; Miner, Nadine E.; Lamb, Christopher C.
- 2017 International Joint Conference on Neural Networks (IJCNN)
A Neuromorphic Approach to Path Integration: A Head-Direction Spiking Neural Network with Vision-driven Reset
conference, January 2018
- Kreiser, Raphaela; Cartiglia, Matteo; Martel, Julien N. P.
- 2018 IEEE International Symposium on Circuits and Systems (ISCAS)
Wide. Fast. Deep: Recent Advances in Multiphoton Microscopy of In Vivo Neuronal Activity
journal, October 2019
- Lecoq, Jérôme; Orlova, Natalia; Grewe, Benjamin F.
- The Journal of Neuroscience, Vol. 39, Issue 46
Vector-based navigation using grid-like representations in artificial agents
journal, May 2018
- Banino, Andrea; Barry, Caswell; Uria, Benigno
- Nature, Vol. 557, Issue 7705
Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation
journal, November 2014
- Khaligh-Razavi, Seyed-Mahdi; Kriegeskorte, Nikolaus
- PLoS Computational Biology, Vol. 10, Issue 11