Abstract
Scientists studying in the fields of AI and neuroscience can learn much from each other, but unfortunately, since about the 1950s, it has been mostly one-sided: neuroscientists have learned from AI, but less so the other way. I argue this is holding back both brain understanding and progress in AI. Current AI (“neural network”/deep learning algorithms) and the brain are very different from each other. The brain does not seem to use trial-and-error–type learning algorithms such as backpropagation to modify weights and more importantly does not require the cumbersome rehearsal needed for trial-and-error implementation. The brain can learn information in a modular and true “one-shot” fashion as the information is encountered while the AI cannot. Instead of backpropagation and rehearsal, there is evidence that the brain regulates its inputs during recognition using regulatory feedback: form the outputs back to inputs—the same inputs that activate the outputs. This is observed through evidence from the fields of neuroscience and cognitive psychology but is not present in current algorithms. Thus, the brain provides an abundance of evidence about its underlying algorithms and while computer science tools and analysis are essential, algorithms guided by computer science should not be standardized into neuroscience theories.
Similar content being viewed by others
References
McClelland JL, McNaughton BL, O’Reilly RC. Why there are complementary learning systems in the hippocampus and neocortex: insights from the successes and failures of connectionist models of learning and memory. Psychol Rev. 1995;102:419–57.
McCloskey M, Cohen NJ. Catastrophic interference in connectionist networks: the sequential learning problem. The psychology of learning and motivation. 1989;24:109–65.
French RM. Catastrophic forgetting in connectionist networks. In: Encyclopedia of cognitive science, vol. 1. Nature Publishing Group, London; 2003. p 431–5.
Coop R, Arel I. Mitigation of catastrophic interference in neural networks using a fixed expansion layer. Midwest Symposium on Circuits and Systems. 2012;726–729.
Moe-Helgesen O-M, Stranden H. Catastrophic forgetting in neural networks. 2005. https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.622.7385&rep=rep1&type=pdf.
Merel J, Botvinick M, Wayne G. Hierarchical motor control in mammals and machines. Nat Commun. 2019;10:5489. https://doi.org/10.1038/s41467-019-13239-6.
Botvinick M, Ritter S, Wang JX, Kurth-Nelson Z, Hassabis D. Reinforcement learning, fast and slow. Trends Cogn Sci. 2019;23:408–22. https://doi.org/10.1016/j.tics.2019.02.006.
Barretto A, Hou S, Borsa D, Silver D, Precup D. Fast reinforcement learning with generalized policy updates. PNAS. 2020;117:30079–87.
Scellier B, Bengio Y. Equilibrium propagation: bridging the gap between energy-based models and backpropagation. Front Comput Neurosci. 2016.
Derdikman D, Whitlock JR, Tsao A, Fyhn M, Hafting T, Moser MB. Fragmentation of grid cell maps in a multicompartment environment. Nat Neurosci. 2009;12(10):1325–32.
Klinzing JG, Niethard N, Born J. Mechanisms of systems memory consolidation during sleep. Nat Neurosci. 2019;22(10):1598–610.
Maingret N, Girardeau G, Todorova R, Goutierre M, Zugaro M. Hippocampo-cortical coupling mediates memory consolidation during sleep. Nat Neurosci. 2016;19(7):959–64.
Buzsáki G. Two-stage model of memory trace formation: a role for “noisy” brain states. Neuroscience. 1989;31(3):551–70.
Carr MF, Jadhav SP, Frank LM. Hippocampal replay in the awake state: a potential substrate for memory consolidation and retrieval. Nat Neurosci. 2011;14(2):147.
Epsztein J. Mental replays enable flexible navigation. Nature. 2022;605:35–6.
Lake BM, Salakhutdinov R, Tenenbaum JB. Human-level concept learning through probabilistic program induction. Science. 2015;350(6266):1332–8.
Lake BM, Salakhutdinov R, Tenenbaum JB. The Omniglot challenge: A 3-year progress report. Behav Sci. 2019;335(29):97–104.
Koch I, Itti NL, Koch C, Niebur E. A model of saliency-based visual attention for rapid scene analysis. In: IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. V20, No. 11. 1998. p 1254–9.
Rosenholtz R. Search asymmetries? What search asymmetries? Percept Psychophys. 2001;63(3):476–89.
Duncan J, Humphreys GW. Visual-search and stimulus similarity. Psychol Rev. 1989;96(3):433–58.
Wolfe JM. Asymmetries in visual search: an introduction. Percept Psychophys. 2001;63(3):p381–9.
Francis G, Cho Y. Effects of temporal integration on the shape of visual backward masking functions. J Exp Psychol Hum Percept Perform. 2008;34:1116–28.
Rinberg D, Koulakov A. Gelperin A speed accuracy tradeoff in olfaction. Neuron. 2006;51(3):351–8.
Xue M, Atallah BV, Scanziani M. Equalizing excitation-inhibition ratios across visual cortical neurons. Nature. 2014;511:596–600.
Denève S, Machens C. Efficient codes and balanced networks. Nat Neurosci. 2016;19:375–82. https://doi.org/10.1038/nn.4243.
Shanglin Z, Yuguo Y. Synaptic E-I balance underlies efficient neural coding. Front Neurosci. 2018. www.frontiersin.org/articles/10.3389/fnins.2018.00046/full
Sadeh S, Clopath C. Excitatory-inhibitory balance modulates the formation and dynamics of neuronal assemblies in cortical networks. Nature Rev. 2021;22:21–37.
Lakatos P, Shah AS, Knuth KH, Ulbert I, Karmos G, Schroeder CE. An oscillatory hierarchy controlling neuronal excitability and stimulus processing in the auditory cortex J Neurophys. 2005;94:1904–11.
Marder E, Goaillard JM. Variability, compensation and homeostasis in neuron and network function. Nat Rev Neurosci. 2006;7:563–74. https://doi.org/10.1038/nrn1949.
Zenke F, Gerstner W, Ganguli S. The temporal paradox of Hebbian learning and homeostatic plasticity. Curr Opin Neurobiol. 2017.
Turrigiano G. Homeostatic synaptic plasticity: local and global mechanisms for stabilizing neuronal function. Cold Spring Harb Perspect Biol. 2012.
Wilson HR, Cowan JD. Excitatory and inhibitory interactions in localized populations of model neurons. Biophys J. 1972;12(1):1–24.
Brunel N. Dynamics of sparsely connected networks of excitatory and inhibitory spiking neurons. J Comput Neurosci. 2000;8(3):183–208.
Rao & Ballard. Predictive coding in the visual cortex: a functional interpretation of some extra-classical receptive-field effects. Nat Neurosci. 1999;2(1):79–87.
Friston K. The free-energy principle: a unified brain theory. Nat Rev Neurosci. 2010;11:127–38. https://doi.org/10.1038/nrn2787.
Hawkins J, Blakeslee S. On intelligence. Times Books. ISBN 0–8050–7456–2. 2004.
Clark A. Whatever next? Predictive brains, situated agents, and the future of cognitive science, Behavioral and Brain Sciences. 2013;36:181–253.
Butz MV. Event-predictive cognition: a root for conceptual human thought. Top Cogn Sci. 2021;13:10–24. https://doi.org/10.1111/tops.12522.
Butz MV. Towards strong AI. Künstlische Intelligenz. 2021;35:91–101. https://doi.org/10.1007/s13218-021-00705-x.
Desimone R, Duncan J. Neural mechanism of selective visual attention. Annu Rev Neurosci. 1995;18:193–222.
Ioannidis JP. Why most published research findings are false. PLoS Med. 2005;2(8):e124. https://doi.org/10.1371/journal.pmed.0020124. PMC 1182327. PMID 16060722.
https://en.wikipedia.org/wiki/Replication_crisis. Accessed 13 Sept 2023.
Camerer CF, Dreber A, Holzmeister F, Ho TH, Huber J, Johannesson M, et al. Evaluating the replicability of social science experiments in Nature and Science between 2010 and 2015. Nat Hum Behav. 2018;2(9):637–44. https://doi.org/10.1038/s41562-018-0399-z. PMID 31346273. S2CID 52098703.
Open Science Collaboration. Psychology. Estimating the reproducibility of psychological science. Science. 2015;349(6251).
Dacrema, P Cremonesi, D Jannach. Are we really making much progress? A worrying analysis of recent neural recommendation approaches. In: Proceedings of the 13th ACM Conference on Recommender Systems, vol. 13. 2019. p 101–9.
Neuroskeptic. fMRI gets slap in the face with a dead fish. Discover Magazine. 2009. www.discovermagazine.com/mind/fmri-gets-slap-in-the-face-with-a-dead-fish.
Madrigal A. Scanning dead salmon in fMRI machine highlights risk of red herrings. Wired. 2009. www.wired.com/2009/09/fmrisalmon/.
Hopfield JJ. Neural networks and physical systems with emergent collective computational abilities PNAS, v79.8. 1982. p 2554–8.
Achler T. Are assumptions of brain recognition correct? 2020. youtube.com/watch?v=F-GBIZoZ1mI&list=PL4nMP8F3B7bg3cNWWwLG8BX-wER2PeB-3&index=1.
Achler T. Neural phenomena focus. 2016. https://youtu.be/9gTJorBeLi8.
Achler T. Symbolic neural networks for cognitive capacities. Biol Inspired Cog Arch. 2014;9:71–81.
Spratling MW. A predictive coding model of gaze shifts and the underlying neurophysiology. Vis Cogn 2017;25(7-8):770–801.
Achler T. Input shunt networks. Neurocomputing. 2001;44–46c:249–255.
Hebb DO. The organization of behavior. New York: Wiley & Sons; 1949.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Human and Animal Rights and Informed Consent
This article does not contain any studies with human participants or animals performed by any of the authors. The author is the founder of Optimizing Mind, Palo Alto, CA.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Achler, T. What AI, Neuroscience, and Cognitive Science Can Learn from Each Other: An Embedded Perspective. Cogn Comput (2023). https://doi.org/10.1007/s12559-023-10194-9
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s12559-023-10194-9