pith. the verified trust layer for science. sign in

arxiv: 2507.10722 · v2 · submitted 2025-07-14 · 🧬 q-bio.NC · cs.NE

Bridging Brains and Machines: A Unified Frontier in Neuroscience, Artificial Intelligence, and Neuromorphic Systems

Pith reviewed 2026-05-19 04:34 UTC · model grok-4.3

classification 🧬 q-bio.NC cs.NE
keywords neuroscienceartificial general intelligenceneuromorphic computingsynaptic plasticityspike-based communicationbrain-inspired hardwareunified research paradigm
0
0 comments X p. Extension

The pith

Neuroscience principles like synaptic plasticity and sparse signaling are supplying design rules for more efficient and adaptable AGI systems on neuromorphic hardware.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper claims that brain physiology supplies concrete blueprints for advancing artificial general intelligence by linking biological features such as changing synaptic strengths, sparse spike messages between neurons, and the binding of multiple senses into unified experiences. It reviews how these map onto current AI methods including attention mechanisms in transformers and the pre-training of large foundation models, while also covering hardware that moves computation into memory to approach the brain's low power use. The authors identify four specific barriers that must be cleared for this convergence to produce working systems that learn continuously, combine language with physical action, and remain under ethical control. A sympathetic reader would see this as a call to treat neuroscience not just as inspiration but as an engineering source for the next generation of intelligent machines.

Core claim

The paper establishes that neuroscience, artificial general intelligence, and neuromorphic computing are converging toward a single unified research paradigm. Using a framework based in brain physiology, it shows how synaptic plasticity, sparse spike-based communication, and multimodal association offer practical design principles for AGI that can blend human-like and machine capabilities. The review maps historical connectionist models through to modern transformers and multi-agent systems, highlighting parallels with cortical mechanisms and memory consolidation, and points to physical devices such as memristive crossbars and photonic arrays as routes to brain-scale efficiency in silicon.

What carries the argument

The physiology-grounded framework that treats synaptic plasticity, sparse spike-based communication, and multimodal association as core mechanisms for guiding AGI architectures and neuromorphic hardware choices.

If this is right

  • AGI systems can achieve continuous lifelong learning without catastrophic forgetting by adopting brain-like plasticity rules.
  • Memristive crossbars and in-memory compute arrays can deliver brain-scale energy efficiency by eliminating the von Neumann bottleneck.
  • Unifying language processing with sensorimotor learning in embodied agents will require new architectures that mirror multimodal association in the brain.
  • Ethical safeguards must be built into neuromorphic autonomous systems from the start to handle their increased independence.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • This convergence suggests that hardware prototypes could be tested directly against biological benchmarks for learning speed and adaptability.
  • Progress here may create new roles for neuroscientists in AI development teams focused on validating brain-inspired mechanisms.
  • The approach could extend to multi-agent systems where each agent maintains separate episodic-like memory stores for more robust collective behavior.

Load-bearing premise

The observed parallels between brain processes and AI techniques are strong and specific enough to generate reliable, actionable engineering principles rather than loose analogies.

What would settle it

Build a large language model that uses spiking neurons for communication and measure whether it matches standard transformer accuracy on benchmark tasks while consuming at least ten times less energy per inference.

read the original abstract

This position and survey paper identifies the emerging convergence of neuroscience, artificial general intelligence (AGI), and neuromorphic computing toward a unified research paradigm. Using a framework grounded in brain physiology, we highlight how synaptic plasticity, sparse spike-based communication, and multimodal association provide design principles for next-generation AGI systems that potentially combine both human and machine intelligences. The review traces this evolution from early connectionist models to state-of-the-art large language models, demonstrating how key innovations like transformer attention, foundation-model pre-training, and multi-agent architectures mirror neurobiological processes like cortical mechanisms, working memory, and episodic consolidation. We then discuss emerging physical substrates capable of breaking the von Neumann bottleneck to achieve brain-scale efficiency in silicon: memristive crossbars, in-memory compute arrays, and emerging quantum and photonic devices. There are four critical challenges at this intersection: 1) integrating spiking dynamics with foundation models, 2) maintaining lifelong plasticity without catastrophic forgetting, 3) unifying language with sensorimotor learning in embodied agents, and 4) enforcing ethical safeguards in advanced neuromorphic autonomous systems. This combined perspective across neuroscience, computation, and hardware offers an integrative agenda for in each of these fields.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

2 major / 2 minor

Summary. This position and survey paper claims an emerging convergence of neuroscience, AGI, and neuromorphic computing into a unified paradigm. Grounded in brain physiology, it argues that synaptic plasticity, sparse spike-based communication, and multimodal association supply design principles for next-generation systems that integrate human and machine intelligence. The manuscript traces developments from early connectionist models through transformers and foundation models, mapping innovations such as attention mechanisms and pre-training onto cortical processes and episodic consolidation. It reviews hardware substrates (memristive crossbars, in-memory compute, photonic and quantum devices) for brain-scale efficiency and enumerates four challenges: integrating spiking dynamics with foundation models, lifelong plasticity without catastrophic forgetting, unifying language with sensorimotor learning in embodied agents, and enforcing ethical safeguards in neuromorphic autonomous systems.

Significance. If the asserted parallels can be converted into concrete, testable design rules, the synthesis could usefully orient research at the neuroscience-AI-hardware intersection and accelerate development of energy-efficient, lifelong-learning systems. The paper's value lies in its cross-disciplinary framing and explicit listing of open challenges rather than in new empirical results or derivations.

major comments (2)
  1. [Abstract and framework section] Abstract and opening framework section: the central assertion that neurobiological processes 'provide design principles' for AGI is load-bearing yet remains at the level of asserted analogy without quantitative mapping, ablation evidence, or documented cases in which explicit adoption of the neurobiological framing produced measurable performance or efficiency gains in any of the four challenge domains.
  2. [Evolution tracing section] Section tracing evolution from connectionist models to transformers: parallels between transformer attention and cortical mechanisms, and between foundation-model pre-training and episodic consolidation, are presented as mirroring neurobiological processes but lack any error analysis, benchmark comparisons, or falsifiable predictions that would allow readers to assess the strength or actionability of the claimed correspondence.
minor comments (2)
  1. [Challenges section] The four challenges are enumerated but receive only high-level description; adding one or two concrete literature pointers or preliminary solution sketches per challenge would improve clarity without altering scope.
  2. [Hardware discussion] Notation for hardware substrates (memristive crossbars, in-memory arrays) is introduced without a brief comparison table of energy or latency metrics relative to von Neumann baselines; such a table would aid readers outside neuromorphic hardware.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive and detailed review. The comments correctly identify that our position and survey paper relies on conceptual synthesis rather than new quantitative evidence. We address each major comment below and outline targeted revisions to clarify the scope and evidential basis of the claimed parallels.

read point-by-point responses
  1. Referee: [Abstract and framework section] Abstract and opening framework section: the central assertion that neurobiological processes 'provide design principles' for AGI is load-bearing yet remains at the level of asserted analogy without quantitative mapping, ablation evidence, or documented cases in which explicit adoption of the neurobiological framing produced measurable performance or efficiency gains in any of the four challenge domains.

    Authors: We agree that the central assertion is presented primarily through conceptual mapping rather than direct quantitative validation. As a position and survey paper, the manuscript synthesizes existing literature to propose integrative directions rather than reporting new experiments, ablations, or performance benchmarks. We will revise the abstract and framework section to explicitly frame the neurobiological processes as inspirational design principles supported by cited prior work, while noting the current lack of comprehensive quantitative mappings. Where possible, we will add brief references to documented cases (e.g., sparsity in neuromorphic hardware yielding efficiency gains) to illustrate the practical relevance of the framing without overstating the evidence. revision: yes

  2. Referee: [Evolution tracing section] Section tracing evolution from connectionist models to transformers: parallels between transformer attention and cortical mechanisms, and between foundation-model pre-training and episodic consolidation, are presented as mirroring neurobiological processes but lack any error analysis, benchmark comparisons, or falsifiable predictions that would allow readers to assess the strength or actionability of the claimed correspondence.

    Authors: The evolution-tracing section provides a historical and conceptual overview drawn from the literature, highlighting interpretive parallels rather than conducting a formal comparative study. We acknowledge that this leaves the strength of the correspondences open to reader interpretation without accompanying error analyses or benchmarks. We will revise this section to include an explicit discussion of the limitations of these analogies, reference any existing comparative studies in the surveyed domains, and add a short forward-looking paragraph proposing specific falsifiable predictions and evaluation approaches that future empirical work could pursue. This addition will help readers gauge actionability while preserving the survey character of the paper. revision: yes

Circularity Check

0 steps flagged

No significant circularity in survey and position paper

full rationale

This manuscript is a literature review and position statement that surveys parallels between neurobiological processes and AI architectures without any mathematical derivations, equations, fitted parameters, or predictive claims that could reduce to inputs by construction. The central narrative traces historical developments and identifies four challenges but offers no load-bearing self-citations, uniqueness theorems, or ansatzes that are justified only internally; all referenced concepts are drawn from the external literature. Because no derivation chain exists to inspect, the paper is self-contained as a descriptive synthesis rather than a formal proof or model.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the domain assumption that brain physiology supplies useful design principles for AGI and that the four listed challenges are the primary integration barriers; no free parameters or new entities are introduced.

axioms (1)
  • domain assumption Brain physiology provides useful design principles for next-generation AGI systems.
    Stated in the opening framework grounded in brain physiology.

pith-pipeline@v0.9.0 · 5945 in / 1326 out tokens · 80076 ms · 2026-05-19T04:34:28.286274+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

300 extracted references · 300 canonical work pages · 18 internal anchors

  1. [1]

    Santiago ramón y cajal and methods in neurohistology.Trends in neurosciences, 15(7):237–246, 1992

    Javier DeFelipe and Edward G Jones. Santiago ramón y cajal and methods in neurohistology.Trends in neurosciences, 15(7):237–246, 1992

  2. [2]

    Sherrington

    Charles S. Sherrington. The Integrative Action of the Nervous System.Science

  3. [3]

    O. Loewi. Über humorale übertragbarkeit der herznervenwirkung.Pflüger’s Archiv für die gesamte Physiologie des Menschen und der Tiere, 189(1):239–242

  4. [4]

    Oxford University Press

    Ivan Petrovich Pavlov.Conditioned Reflexes: An Investigation of the Physiological Activity of the Cerebral Cortex. Oxford University Press

  5. [5]

    McCulloch and Walter Pitts

    Warren S. McCulloch and Walter Pitts. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4):115–133

  6. [6]

    Donald O. Hebb. The organization of behavior: A neuropsychological theory.Science Education, 34:336–337, 1950. Published in December 1950

  7. [7]

    Hodgkin and huxley and the basis for electrical sig- nalling: a remarkable legacy still going strong.The Journal of physiology, 590(Pt 11):2569, 2012

    Jamie I Vandenberg and Stephen G Waxman. Hodgkin and huxley and the basis for electrical sig- nalling: a remarkable legacy still going strong.The Journal of physiology, 590(Pt 11):2569, 2012

  8. [8]

    Recounting the impact of hubel and wiesel.The Journal of physiology, 587(12):2817– 2823, 2009

    Robert H Wurtz. Recounting the impact of hubel and wiesel.The Journal of physiology, 587(12):2817– 2823, 2009

  9. [9]

    Human memory: A proposed system and its control processes

    Richard C Atkinson and Richard M Shiffrin. Human memory: A proposed system and its control processes. InPsychology of learning and motivation, volume 2, pages 89–195. Elsevier, 1968

  10. [10]

    Baddeley and Graham Hitch

    Alan D. Baddeley and Graham Hitch. Working Memory. In Gordon H. Bower, editor,Psychology of Learning and Motivation, volume 8, pages 47–89. Academic Press

  11. [11]

    A. M. Turing. Computing machinery and intelligence.Mind, 59(236):433–460, 1950

  12. [12]

    The past and future of ai.Boston Review, 46(2):139–162, April 2021

    Kenneth Taylor. The past and future of ai.Boston Review, 46(2):139–162, April 2021

  13. [13]

    Smolensky

    P. Smolensky. Connectionist AI, symbolic AI, and the brain.Artificial Intelligence Review, 1(2):95– 109, June 1987

  14. [14]

    The Rise of Intelligent Machines

    Shamik Tiwari. The Rise of Intelligent Machines. InArtificial Intelligence and Machine Learning in Drug Design and Development, pages 1–22. John Wiley & Sons, Ltd, 2024. 53 BRIDGINGBRAINS ANDMACHINES: A UNIFIEDFRONTIER INNEUROSCIENCE, ARTIFICIAL INTELLIGENCE,ANDNEUROMORPHICSYSTEMS

  15. [15]

    Xuanzhe Liu, Diandian Gu, Zhenpeng Chen, Jinfeng Wen, Zili Zhang, Yun Ma, Haoyu Wang, and Xin Jin. Rise of Distributed Deep Learning Training in the Big Model Era: From a Software Engineer- ing Perspective.ACM Transactions on Software Engineering and Methodology, 32(6):156:1–156:26, September 2023

  16. [16]

    Haoyi Xiong, Zhiyuan Wang, Xuhong Li, Jiang Bian, Zeke Xie, Shahid Mumtaz, and Laura E. Barnes. Converging paradigms: The synergy of symbolic and connectionist ai in llm-empowered autonomous agents, 2024. arXiv preprint arXiv:2407.08516

  17. [17]

    On the Power of Foundation Models

    Yang Yuan. On the power of foundation models.arXiv preprint arXiv:2211.16327, 2024. Accepted at ICML 2023

  18. [18]

    Towards artificial general intelligence via a multi- modal foundation model.Nature Communications, 13(1):3094, 2022

    Nanyi Fei, Zhiwu Lu, Yizhao Gao, Guoxing Yang, Yuqi Huo, Jingyuan Wen, Haoyu Lu, Ruihua Song, Xin Gao, Tao Xiang, Hao Sun, and Ji-Rong Wen. Towards artificial general intelligence via a multi- modal foundation model.Nature Communications, 13(1):3094, 2022

  19. [19]

    The pragmatic agi era: Recognizing the general intelligence unlocked by trans- formers.https://sciety.org/articles/activity/10.31219/osf.io/9ybmw_v1, April 2025

    Rafael Cardeal Tavares. The pragmatic agi era: Recognizing the general intelligence unlocked by trans- formers.https://sciety.org/articles/activity/10.31219/osf.io/9ybmw_v1, April 2025. OSF Preprints, DOI: 10.31219/osf.io/9ybmw

  20. [20]

    Nav- igating artificial general intelligence development: societal, technological, ethical, and brain-inspired pathways.Scientific Reports, 15(1):8443, 2025

    Raghu Raman, Robin Kowalski, Krishnashree Achuthan, Akshay Iyer, and Prema Nedungadi. Nav- igating artificial general intelligence development: societal, technological, ethical, and brain-inspired pathways.Scientific Reports, 15(1):8443, 2025

  21. [21]

    Introducing gemini: Our largest and most capable ai model.https://blog.google/ technology/ai/google-gemini-ai/, 2023

    Google. Introducing gemini: Our largest and most capable ai model.https://blog.google/ technology/ai/google-gemini-ai/, 2023. Accessed: 2025-06-02

  22. [22]

    Introducing the next generation of claude.https://www.anthropic.com/news/ claude-3-family, 2024

    Anthropic. Introducing the next generation of claude.https://www.anthropic.com/news/ claude-3-family, 2024. Accessed: 2025-06-02

  23. [23]

    Foundation model.https://en.wikipedia.org/wiki/ Foundation_model, 2025

    Wikipedia contributors. Foundation model.https://en.wikipedia.org/wiki/ Foundation_model, 2025. Accessed: 2025-06-02

  24. [24]

    Addison-Wesley, 1989

    Carver Mead.Analog VLSI and neural systems. Addison-Wesley, 1989

  25. [25]

    Neuromorphic electronic systems.Proceedings of the IEEE, 78(10):1629–1636, 1990

    Carver Mead. Neuromorphic electronic systems.Proceedings of the IEEE, 78(10):1629–1636, 1990

  26. [26]

    A silicon model of early visual processing.Neural networks, 1(1):91–97, 1988

    Misha A Mahowald and Carver A Mead. A silicon model of early visual processing.Neural networks, 1(1):91–97, 1988

  27. [27]

    PhD thesis, California Institute of Technology, 1992

    Misha A Mahowald.VLSI analogs of neuronal visual processing: A synthesis of form and function. PhD thesis, California Institute of Technology, 1992

  28. [28]

    Neuromorphic Sili- con Neuron Circuits

    Giacomo Indiveri, Bernabé Linares-Barranco, Tara Julia Hamilton, André van Schaik, Ralph Etienne- Cummings, Tobi Delbruck, Shih-Chii Liu, Piotr Dudek, Philipp Häfliger, Sylvie Renaud, Johannes Schemmel, Gert Cauwenberghs, John Arthur, Kai Hynna, Fopefolu Folowosele, Sylvain Saighi, Teresa Serrano-Gotarredona, Jayawan Wijekoon, Yingxue Wang, and Kwabena Bo...

  29. [29]

    The silicon retina.Scientific American, 264(5):76–82, 1991

    Misha A Mahowald and Carver Mead. The silicon retina.Scientific American, 264(5):76–82, 1991

  30. [30]

    A review of the integrate-and-fire neuron model: I

    Anthony N Burkitt. A review of the integrate-and-fire neuron model: I. homogeneous synaptic input. Biological cybernetics, 95(1):1–19, 2006

  31. [31]

    A contrast sensitive silicon retina with reciprocal synapses

    Kwabena A Boahen and Andreas G Andreou. A contrast sensitive silicon retina with reciprocal synapses. InAdvances in neural information processing systems, volume 4, pages 764–772, 1992

  32. [32]

    Wiley, 1949

    Donald Olding Hebb.The organization of behavior: A neuropsychological theory. Wiley, 1949

  33. [33]

    A neuronal learning rule for sub-millisecond temporal coding.Nature, 383(6595):76–78, 1996

    Wulfram Gerstner, Richard Kempter, J Leo Van Hemmen, and Hermann Wagner. A neuronal learning rule for sub-millisecond temporal coding.Nature, 383(6595):76–78, 1996

  34. [34]

    Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type.Journal of neuroscience, 18(24):10464– 10472, 1998

    Guo-qiang Bi and Mu-ming Poo. Synaptic modifications in cultured hippocampal neurons: dependence on spike timing, synaptic strength, and postsynaptic cell type.Journal of neuroscience, 18(24):10464– 10472, 1998. 54 BRIDGINGBRAINS ANDMACHINES: A UNIFIEDFRONTIER INNEUROSCIENCE, ARTIFICIAL INTELLIGENCE,ANDNEUROMORPHICSYSTEMS

  35. [35]

    Vlsi implementation of spike timing dependent plasticity

    Adria Bofill-i Petit and Alan F Murray. Vlsi implementation of spike timing dependent plasticity. In 2004 IEEE International Symposium on Circuits and Systems (IEEE Cat. No. 04CH37512), volume 5, pages V–121. IEEE, 2004

  36. [36]

    A vlsi array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity.IEEE Transactions on neural networks, 17(1):211–221, 2006

    Giacomo Indiveri, Elisabetta Chicca, and Rodney Douglas. A vlsi array of low-power spiking neurons and bistable synapses with spike-timing dependent plasticity.IEEE Transactions on neural networks, 17(1):211–221, 2006

  37. [37]

    Point-to-point connectivity between neuromorphic chips using address events

    Kwabena A Boahen. Point-to-point connectivity between neuromorphic chips using address events. IEEE Transactions on Circuits and Systems II: Analog and Digital Signal Processing, 47(5):416–434, 2000

  38. [38]

    Sivilotti.Wiring considerations in analog VLSI systems, with application to field- programmable networks

    Massimo A. Sivilotti.Wiring considerations in analog VLSI systems, with application to field- programmable networks. PhD thesis, California Institute of Technology, 1991

  39. [39]

    Can programming be liberated from the von neumann style?: a functional style and its algebra of programs.Communications of the ACM, 21(8):613–641, 1978

    John Backus. Can programming be liberated from the von neumann style?: a functional style and its algebra of programs.Communications of the ACM, 21(8):613–641, 1978

  40. [40]

    Neurogrid: A mixed-analog-digital multichip system for large-scale neural simulations.Proceedings of the IEEE, 102(5):699–716, 2014

    Ben V Benjamin, Peiran Gao, Emmett McQuinn, Swadesh Choudhary, Anand R Chandrasekaran, Jean-Marie Bussat, Rodrigo Alvarez-Icaza, John V Arthur, Paul A Merolla, and Kwabena Boahen. Neurogrid: A mixed-analog-digital multichip system for large-scale neural simulations.Proceedings of the IEEE, 102(5):699–716, 2014

  41. [41]

    A million spiking-neuron integrated circuit with a scalable communication network and interface.Science, 345(6197):668–673, 2014

    Paul A Merolla, John V Arthur, Rodrigo Alvarez-Icaza, Andrew S Cassidy, Jun Sawada, Filipp Akopyan, Bryan L Jackson, Nabil Imam, Chen Guo, Yutaka Banda, et al. A million spiking-neuron integrated circuit with a scalable communication network and interface.Science, 345(6197):668–673, 2014

  42. [42]

    The spinnaker project.Proceed- ings of the IEEE, 102(5):652–665, 2014

    Steve B Furber, Francesco Galluppi, Steve Temple, and Luis A Plana. The spinnaker project.Proceed- ings of the IEEE, 102(5):652–665, 2014

  43. [43]

    A wafer-scale neuromorphic hardware system for large-scale neural modeling

    Johannes Schemmel, Andreas Grübl, Karlheinz Meier, and Eva Mueller. A wafer-scale neuromorphic hardware system for large-scale neural modeling. In2010 IEEE International Symposium on Circuits and Systems (ISCAS), pages 1947–1950. IEEE, 2010

  44. [44]

    Loihi: A neuromorphic manycore processor with on-chip learning.IEEE Micro, 38(1):82–99, 2018

    Mike Davies, Narayan Srinivasa, Tsung-Han Lin, Gautham Chinya, Yongqiang Cao, Sri Harsha Cho- day, Georgios Dimou, Prasad Joshi, Nabil Imam, Shweta Jain, et al. Loihi: A neuromorphic manycore processor with on-chip learning.IEEE Micro, 38(1):82–99, 2018

  45. [45]

    McCulloch and Walter Pitts

    Warren S. McCulloch and Walter Pitts. A logical calculus of the ideas immanent in nervous activity. The bulletin of mathematical biophysics, 5(4):115–133, December 1943

  46. [46]

    Neural networks and physical systems with emergent collective computational abilities

    J J Hopfield. Neural networks and physical systems with emergent collective computational abilities. 79(8):2554–2558

  47. [47]

    A Mathematical Theory of Communication

    C E Shannon. A Mathematical Theory of Communication

  48. [48]

    Some informational aspects of visual perception

    Fred Attneave. Some informational aspects of visual perception. 61(3):183–193

  49. [49]

    H. B. Barlow. Possible Principles Underlying the Transformations of Sensory Messages. In Walter A. Rosenblith, editor,Sensory Communication, pages 216–234. The MIT Press

  50. [50]

    Rosenblatt

    F. Rosenblatt. The perceptron: A probabilistic model for information storage and organization in the brain. 65(6):386–408

  51. [51]

    Knill and Alexandre Pouget

    David C. Knill and Alexandre Pouget. The Bayesian brain: The role of uncertainty in neural coding and computation. 27(12):712–719

  52. [52]

    Papert.Perceptrons: An Introduction to Computational Geometry

    Marvin Minsky and Seymour A. Papert.Perceptrons: An Introduction to Computational Geometry. The MIT Press

  53. [53]

    Springer US

    Carver Mead and Mohammed Ismail, editors.Analog VLSI Implementation of Neural Systems, vol- ume 80 ofThe Kluwer International Series in Engineering and Computer Science. Springer US

  54. [54]

    Self-organized formation of topologically correct feature maps

    Teuvo Kohonen. Self-organized formation of topologically correct feature maps. 43(1):59–69. 55 BRIDGINGBRAINS ANDMACHINES: A UNIFIEDFRONTIER INNEUROSCIENCE, ARTIFICIAL INTELLIGENCE,ANDNEUROMORPHICSYSTEMS

  55. [55]

    Gomez, Łukasz Kaiser, and Illia Polosukhin

    Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, Łukasz Kaiser, and Illia Polosukhin. Attention is all you need. InAdvances in Neural Information Processing Systems, volume 30, pages 5998–6008, 2017

  56. [56]

    Hosseini, Nancy Kan- wisher, Joshua B

    Martin Schrimpf, Idan Asher Blank, Greta Tuckute, Carina Kauf, Eghbal A. Hosseini, Nancy Kan- wisher, Joshua B. Tenenbaum, and Evelina Fedorenko. The neural architecture of language: Integrative modeling converges on predictive processing. 118(45):e2105646118

  57. [57]

    Hosseini, Martin Schrimpf, Yian Zhang, Samuel Bowman, Noga Zaslavsky, and Evelina Fedorenko

    Eghbal A. Hosseini, Martin Schrimpf, Yian Zhang, Samuel Bowman, Noga Zaslavsky, and Evelina Fedorenko. Artificial Neural Network Language Models Predict Human Brain Responses to Language Even After a Developmentally Realistic Amount of Training. 5(1):43–63

  58. [58]

    Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation

    Xin Liu, Ziyue Zhang, and Jingxin Nie. Talking to the brain: Using Large Language Models as Proxies to Model Brain Semantic Representation

  59. [59]

    Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?

    Byung-Doh Oh and William Schuler. Why Does Surprisal From Larger Transformer-Based Language Models Provide a Poorer Fit to Human Reading Times?

  60. [60]

    Kastanenka, and Dmitry Krotov

    Leo Kozachkov, Ksenia V . Kastanenka, and Dmitry Krotov. Building transformers from neurons and astrocytes. 120(34):e2219150120

  61. [61]

    Ian T. Ellwood. Short-term Hebbian learning can implement transformer-like attention. 20(1):e1011843

  62. [62]

    A Biologically Inspired Attention Model for Neural Signal Analysis

    Nicolas Skatchkovsky, Natalia Glazman, Sadra Sadeh, and Florencia Iacaruso. A Biologically Inspired Attention Model for Neural Signal Analysis

  63. [63]

    Multihead self-attention in cortico-thalamic circuits

    Arno Granier and Walter Senn. Multihead self-attention in cortico-thalamic circuits

  64. [64]

    Churchland, and Terrence J

    Lyle Muller, Patricia S. Churchland, and Terrence J. Sejnowski. Transformers and cortical waves: Encoders for pulling in context across time. 47(10):788–802

  65. [65]

    Justin Lee

    Jea Kwon, Sungjun Lim, Kyungwoo Song, and C. Justin Lee. Brain-inspired lp-convolution benefits large kernels and aligns better with visual cortex. 2025. Accepted at ICLR 2025

  66. [66]

    Mechanisms of circumferential gyral convolution in primate brains

    Tuo Zhang, Mir Jalil Razavi, Hanbo Chen, Yujie Li, Xiao Li, Longchuan Li, Lei Guo, Xiaoping Hu, Tianming Liu, and Xianqiao Wang. Mechanisms of circumferential gyral convolution in primate brains. Journal of Computational Neuroscience, 42(3):217–229, 2024

  67. [67]

    Huth, prefix=de useprefix=true family=Heer, given=Wendy A., Thomas L

    Alexander G. Huth, prefix=de useprefix=true family=Heer, given=Wendy A., Thomas L. Griffiths, Frédéric E. Theunissen, and Jack L. Gallant. Natural speech reveals the semantic maps that tile human cerebral cortex. 532(7600):453–458

  68. [68]

    Brain transformers: Integrating spiking neu- ral networks with large language models for energy-efficient sequence modeling.arXiv preprint arXiv:2408.12345, 2024

    Shuo Tang, Wei Li, Ying Liu, and Haoran Zhou. Brain transformers: Integrating spiking neu- ral networks with large language models for energy-efficient sequence modeling.arXiv preprint arXiv:2408.12345, 2024

  69. [69]

    Caffo, David H

    Lena Smirnova, Brian S. Caffo, David H. Gracias, Qi Huang, Itzy E. Morales Pantoja, Bohao Tang, Donald J. Zack, Cynthia A. Berlinicke, J. Lomax Boyd, Timothy D. Harris, Erik C. Johnson, Brett J. Kagan, Jeffrey Kahn, Alysson R. Muotri, Barton L. Paulhamus, Jens C. Schwamborn, Jesse Plotkin, Alexander S. Szalay, Joshua T. V ogelstein, Paul F. Worley, and Th...

  70. [70]

    Organoid intelligence and biocomputing advances: Current steps and future directions

    Al-Hassan Soliman Wadan. Organoid intelligence and biocomputing advances: Current steps and future directions. 3:8–14

  71. [71]

    Scharf-Deering, and Jeantine E

    Insoo Hyun, J.C. Scharf-Deering, and Jeantine E. Lunshof. Ethical Issues Related to Brain Organoid Research. 1732:146653

  72. [72]

    Meta-Learning in Spiking Neural Networks with Reward-Modulated STDP

    Arsham Gholamzadeh Khoee, Alireza Javaheri, Saeed Reza Kheradpisheh, and Mohammad Gan- jtabesh. Meta-Learning in Spiking Neural Networks with Reward-Modulated STDP

  73. [73]

    Loihi 2: A neuromorphic processor with increased channel capacity and embedded processor cores.IEEE Micro, 43(4):12–23, 2023

    Mike Davies, Josh Sullivan, Yolo Khwa, et al. Loihi 2: A neuromorphic processor with increased channel capacity and embedded processor cores.IEEE Micro, 43(4):12–23, 2023

  74. [74]

    Smith, Trevor Bihl, and Jundong Liu

    Ye Yue, Marc Baltes, Nidal Abujahar, Tao Sun, Charles D. Smith, Trevor Bihl, and Jundong Liu. Hybrid Spiking Neural Network Fine-tuning for Hippocampus Segmentation. 56 BRIDGINGBRAINS ANDMACHINES: A UNIFIEDFRONTIER INNEUROSCIENCE, ARTIFICIAL INTELLIGENCE,ANDNEUROMORPHICSYSTEMS

  75. [75]

    Eshraghian

    Rui-Jie Zhu, Qihang Zhao, Guoqi Li, and Jason K. Eshraghian. SpikeGPT: Generative Pre-trained Language Model with Spiking Neural Networks

  76. [76]

    Spikformer: When Spiking Neural Network Meets Transformer

    Zhaokun Zhou, Yuesheng Zhu, Chao He, Yaowei Wang, Shuicheng Yan, Yonghong Tian, and Li Yuan. Spikformer: When Spiking Neural Network Meets Transformer

  77. [77]

    SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation

    Malyaban Bal and Abhronil Sengupta. SpikingBERT: Distilling BERT to Train Spiking Language Models Using Implicit Differentiation. 38(10):10998–11006

  78. [78]

    Jens E. Pedersen, Steven Abreu, Matthias Jobst, Gregor Lenz, Vittorio Fra, Felix Christian Bauer, Dy- lan Richard Muir, Peng Zhou, Bernhard V ogginger, Kade Heckel, Gianvito Urgese, Sadasivan Shankar, Terrence C. Stewart, Sadique Sheik, and Jason K. Eshraghian. Neuromorphic intermediate representa- tion: A unified instruction set for interoperable brain-i...

  79. [79]

    Toward large-scale spiking neural networks: A comprehensive survey and future directions.arXiv preprint arXiv:2409.02111, 2024

    Yangfan Hu, Qian Zheng, Guoqi Li, Huajin Tang, and Gang Pan. Toward large-scale spiking neural networks: A comprehensive survey and future directions.arXiv preprint arXiv:2409.02111, 2024

  80. [80]

    Brain-inspired wiring economics for artificial neural networks

    Xin-Jie Zhang, Jack Murdoch Moore, Ting-Ting Gao, Xiaozhu Zhang, and Gang Yan. Brain-inspired wiring economics for artificial neural networks. 4(1):pgae580

Showing first 80 references.