skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: 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.

Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
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

Crossing the Cleft: Communication Challenges Between Neuroscience and Artificial Intelligence. United States: N. p., 2020. Web. doi:10.3389/fncom.2020.00039.
Crossing the Cleft: Communication Challenges Between Neuroscience and Artificial Intelligence. United States. doi:https://doi.org/10.3389/fncom.2020.00039
Wed . "Crossing the Cleft: Communication Challenges Between Neuroscience and Artificial Intelligence". United States. doi: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 = {None, None},
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 = {2020},
month = {5}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Save / Share:

Works referenced in this record:

Deep convolutional models improve predictions of macaque V1 responses to natural images
journal, April 2019


Deep Neural Networks Reveal a Gradient in the Complexity of Neural Representations across the Ventral Stream
journal, July 2015


Navigating cognition: Spatial codes for human thinking
journal, November 2018

  • Bellmund, Jacob L. S.; Gärdenfors, Peter; Moser, Edvard I.
  • Science, Vol. 362, Issue 6415
  • DOI: 10.1126/science.aat6766

Head-direction cells recorded from the postsubiculum in freely moving rats. II. Effects of environmental manipulations
journal, February 1990


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
  • DOI: 10.1073/pnas.1403112111

Probing Deep Brain Circuitry: New Advances in in Vivo Calcium Measurement Strategies
journal, December 2016


Engineering a Less Artificial Intelligence
journal, September 2019


Sequencing the Connectome
journal, October 2012


A million spiking-neuron integrated circuit with a scalable communication network and interface
journal, August 2014


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
  • DOI: 10.1038/s41593-018-0269-z

Loihi: A Neuromorphic Manycore Processor with On-Chip Learning
journal, January 2018


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
  • DOI: 10.1088/1748-3190/aa5b48

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
  • DOI: 10.7554/eLife.26478

Genetic Approaches to Neural Circuits in the Mouse
journal, July 2013


Evolving Images for Visual Neurons Using a Deep Generative Network Reveals Coding Principles and Neuronal Preferences
journal, May 2019


Selective Attention in an Insect Visual Neuron
journal, January 2013


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
  • DOI: 10.1088/1741-2552/aa776c

To build a brain
journal, August 2012


Neuroscience Needs Behavior: Correcting a Reductionist Bias
journal, February 2017


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
  • DOI: 10.1073/pnas.1611835114

A general reinforcement learning algorithm that masters chess, shogi, and Go through self-play
journal, December 2018


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
  • DOI: 10.1038/21176

Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
journal, January 1962


Neuromorphic Silicon Neuron Circuits
journal, January 2011

  • Indiveri, Giacomo; Linares-Barranco, Bernabé; Hamilton, Tara Julia
  • Frontiers in Neuroscience, Vol. 5
  • DOI: 10.3389/fnins.2011.00073

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
  • DOI: 10.1073/pnas.1803839115

Inception loops discover what excites neurons most using deep predictive models
journal, November 2019


Spatial Representation in the Entorhinal Cortex
journal, August 2004


Accurate Estimation of Neural Population Dynamics without Spike Sorting
journal, July 2019


A Canonical Microcircuit for Neocortex
journal, December 1989

  • Douglas, Rodney J.; Martin, Kevan A. C.; Whitteridge, David
  • Neural Computation, Vol. 1, Issue 4
  • DOI: 10.1162/neco.1989.1.4.480

A deep learning framework for neuroscience
journal, October 2019

  • Richards, Blake A.; Lillicrap, Timothy P.; Beaudoin, Philippe
  • Nature Neuroscience, Vol. 22, Issue 11
  • DOI: 10.1038/s41593-019-0520-2

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
  • DOI: 10.1145/1282280.1282303

Classification of electrophysiological and morphological neuron types in the mouse visual cortex
journal, June 2019


Principles of connectivity among morphologically defined cell types in adult neocortex
journal, November 2015


Head-direction cells recorded from the postsubiculum in freely moving rats. I. Description and quantitative analysis
journal, February 1990


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
  • DOI: 10.1098/rsif.2015.0083

A generative vision model that trains with high data efficiency and breaks text-based CAPTCHAs
journal, October 2017


Spatial cognition and neuro-mimetic navigation: a model of hippocampal place cell activity
journal, August 2000


Functional Imaging and Optogenetics in Drosophila
journal, April 2018


How advances in neural recording affect data analysis
journal, January 2011

  • Stevenson, Ian H.; Kording, Konrad P.
  • Nature Neuroscience, Vol. 14, Issue 2
  • DOI: 10.1038/nn.2731

A Framework for Intelligence and Cortical Function Based on Grid Cells in the Neocortex
journal, January 2019


A Model for the Detection of Moving Targets in Visual Clutter Inspired by Insect Physiology
journal, July 2008


NeuroSLAM: a brain-inspired SLAM system for 3D environments
journal, September 2019


A Complete Electron Microscopy Volume of the Brain of Adult Drosophila melanogaster
journal, July 2018


Effects of Attention on Orientation-Tuning Functions of Single Neurons in Macaque Cortical Area V4
journal, January 1999


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
  • DOI: 10.1038/s42256-018-0015-y

Neural population control via deep image synthesis
journal, May 2019


Neuroscience-Inspired Artificial Intelligence
journal, July 2017


The neocortical circuit: themes and variations
journal, January 2015

  • Harris, Kenneth D.; Shepherd, Gordon M. G.
  • Nature Neuroscience, Vol. 18, Issue 2
  • DOI: 10.1038/nn.3917

High-precision automated reconstruction of neurons with flood-filling networks
journal, July 2018


The hippocampus as a spatial map. Preliminary evidence from unit activity in the freely-moving rat
journal, November 1971


Neural algorithms and computing beyond Moore's law
journal, March 2019

  • Aimone, James B.
  • Communications of the ACM, Vol. 62, Issue 4
  • DOI: 10.1145/3231589

A Survey on Transfer Learning
journal, October 2010

  • Pan, Sinno Jialin; Yang, Qiang
  • IEEE Transactions on Knowledge and Data Engineering, Vol. 22, Issue 10
  • DOI: 10.1109/TKDE.2009.191

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
  • DOI: 10.3389/fncom.2016.00094

Gradient-based learning applied to document recognition
journal, January 1998

  • Lecun, Y.; Bottou, L.; Bengio, Y.
  • Proceedings of the IEEE, Vol. 86, Issue 11
  • DOI: 10.1109/5.726791

Evidence that recurrent circuits are critical to the ventral stream’s execution of core object recognition behavior
journal, April 2019


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)
  • DOI: 10.1109/IJCNN.2018.8489348

Deep learning in spiking neural networks
journal, March 2019


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)
  • DOI: 10.1109/IJCNN.2017.7965898

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)
  • DOI: 10.1109/ISCAS.2018.8351509

Wide. Fast. Deep: Recent Advances in Multiphoton Microscopy of In Vivo Neuronal Activity
journal, October 2019


Vector-based navigation using grid-like representations in artificial agents
journal, May 2018


Deep Supervised, but Not Unsupervised, Models May Explain IT Cortical Representation
journal, November 2014