pith. sign in

arxiv: 2304.01844 · v3 · submitted 2023-04-04 · 💻 cs.AI

Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning

Jingyi Feng , Chenming Zhang This is my paper

Pith reviewed 2026-05-24 09:06 UTC · model grok-4.3

classification 💻 cs.AI
keywords grid cellscognitive learningBayesian reasoningspace-divisionexploration-exploitationneural decodingself-reinforcementbrain mechanism
0
0 comments X

The pith

A grid module can mediate both external interactions and internal self-reinforcement in a cognitive learning system.

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

The paper introduces Grid-SD2E, a system that incorporates a grid module inspired by grid cells to serve as both an interaction medium with the outside world and a self-reinforcement medium inside the system. The space-division and exploration-exploitation component receives 0/1 grid signals and integrates them with Bayesian reasoning to create an interactive, self-reinforcing cognitive framework. Derived from neuroscience experiments and neural decoding experience, the model analyzes its own rationality against existing theories and extracts a smallest computing unit analogous to a single neuron. This setup aims to propose special and general rules for explaining interactions between people and between people and the external world.

Core claim

In the Grid-SD2E system a grid module functions as an interaction medium between the outside world and the system as well as a self-reinforcement medium within the system; the space-division and exploration-exploitation (SD2E) component receives the 0/1 signals of a grid through its space-division module, and the overall framework is a theoretical model that extracts the smallest computing unit analogous to a single neuron in the brain.

What carries the argument

The grid module, which supplies 0/1 signals to the space-division module for both external mediation and internal reinforcement within the SD2E framework.

If this is right

  • The system can propose special and general rules to explain different interactions between people and between people and the external world.
  • The framework supports analysis of its rationality based on existing theories in neuroscience and cognitive science.
  • The smallest computing unit extracted from the framework is analogous to a single neuron in the brain.
  • The grid module enables the system to comprehend brain interactions with the external world through generated neural data.

Where Pith is reading between the lines

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

  • Implementation of the extracted smallest computing unit in artificial systems could test whether the grid-feedback mechanism scales to larger cognitive tasks.
  • The rules proposed for human interactions might be checked against specific datasets of social or environmental behavior not used in the original derivation.
  • Integration of the grid module with other navigation or memory models could reveal whether the self-reinforcement property transfers across domains.

Load-bearing premise

The theoretical model derived from other researchers' experiments and neural decoding experience can propose special and general rules that explain different interactions between people and between people and the external world.

What would settle it

A set of observed human interactions or neural recordings that cannot be accounted for by the proposed special and general rules extracted from the grid-feedback framework would falsify the central claim.

Figures

Figures reproduced from arXiv: 2304.01844 by Chenming Zhang, Jingyi Feng.

Figure 1
Figure 1. Figure 1: (Neural decoding) The (a) interaction and (b) self-reinforcement in a cognitive system. If an arrow exists [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Here, picture (a) comes from [33], picture (b) comes from https://commons.wikimedia.org/wiki/ File:Autocorrelation_image.jpg, and picture (c) comes from [23]. (a) Grey shows the movement trajectory of a foraging rat in a 2.2m wide square enclosure. Black shows the spatial firing pattern of a grid cell from the rat medial entorhinal cortex. Each black dot is one spike of grid cell when the rat moves to that… view at source ↗
Figure 3
Figure 3. Figure 3: (a) Suppose the deflection angle of the x-axis is α and for the y-axis is β (mimicking the tilt shown by the grid cell map in Figure 2b). (b) and (c) are two schemes given under the condition (a), whose purpose is to keep the predicted values and the true labels in the same subspace. Here, the red line is only used as an auxiliary line for reference, and the blue area is an active space. (b) When x- and y-… view at source ↗
Figure 4
Figure 4. Figure 4: (a) The steps of the local method used in Grid-SD2E [ [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: The Smallest computing unit is from Figure 4, which can be compared to a single neuron. [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: (a) In the special rule, the subject (people) interacts with the object (world or environment), excluding [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: A Galton board and an algorithm board [5]. [PITH_FULL_IMAGE:figures/full_fig_p018_7.png] view at source ↗
read the original abstract

Comprehending how the brain interacts with the external world through generated neural data is crucial for determining its working mechanism, treating brain diseases, and understanding intelligence. Although many theoretical models have been proposed, they have thus far been difficult to integrate and develop. In this study, we were inspired in part by grid cells in creating a more general and robust grid module and constructing an interactive and self-reinforcing cognitive system together with Bayesian reasoning, an approach called space-division and exploration-exploitation with grid-feedback (Grid-SD2E). Here, a grid module can be used as an interaction medium between the outside world and a system, as well as a self-reinforcement medium within the system. The space-division and exploration-exploitation (SD2E) receives the 0/1 signals of a grid through its space-division (SD) module. The system described in this paper is also a theoretical model derived from experiments conducted by other researchers and our experience on neural decoding. Herein, we analyse the rationality of the system based on the existing theories in both neuroscience and cognitive science, and attempt to propose special and general rules to explain the different interactions between people and between people and the external world. What's more, based on this framework, the smallest computing unit is extracted, which is analogous to a single neuron in the brain.

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

3 major / 2 minor

Summary. The manuscript proposes Grid-SD2E, a theoretical cognitive learning system that combines a grid module (inspired by grid cells) with Bayesian reasoning in a space-division and exploration-exploitation (SD2E) framework. The grid module is presented as serving dual purposes: mediating interactions between the system and the external world, and providing self-reinforcement internally. The paper derives this from prior experiments and neural decoding experience, analyzes its rationality against neuroscience and cognitive science theories, proposes rules for human interactions, and extracts a minimal computing unit analogous to a neuron.

Significance. If the proposed framework could be formalized with explicit mechanisms and shown to produce the claimed dual-role behavior, it would offer a potentially integrative contribution to cognitive modeling by linking grid-cell-inspired structures to Bayesian SD2E processes. As presented, however, the absence of any supporting derivations or tests means the significance remains that of an untested conceptual proposal.

major comments (3)
  1. [Abstract] Abstract: The central claim that the grid module serves as both an external interaction medium and an internal self-reinforcement medium is defined internally by the SD2E rules the authors introduce, so the claimed self-reinforcement property reduces to the model's own construction rather than an independent benchmark or external derivation.
  2. [System description] System description (throughout): No mathematical derivations, equations, pseudocode, or algorithmic specification is given for how the grid produces 0/1 signals, how the space-division (SD) module processes them, or how exploration-exploitation is implemented within the Bayesian framework. This absence is load-bearing because the manuscript positions the system as a general and robust construction capable of the stated functions.
  3. [Rationality analysis] Rationality analysis section: The analysis of the system's rationality against existing neuroscience and cognitive science theories remains at a high conceptual level without specific model comparisons, quantitative contrasts, or demonstrations that Grid-SD2E resolves documented limitations in prior frameworks.
minor comments (2)
  1. [Abstract] Abstract: The phrasing 'What's more' is informal for a journal article and should be replaced with a more formal transition.
  2. The manuscript would benefit from at least one worked example or minimal formalization to illustrate how the extracted smallest computing unit (analogous to a neuron) is derived from the grid-SD2E rules.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive comments. We address each major point below, agreeing where the manuscript requires clarification or expansion, and outline the corresponding revisions.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The central claim that the grid module serves as both an external interaction medium and an internal self-reinforcement medium is defined internally by the SD2E rules the authors introduce, so the claimed self-reinforcement property reduces to the model's own construction rather than an independent benchmark or external derivation.

    Authors: We agree that the dual role is defined within the SD2E rules as part of the proposed construction. This is by design, as the rules are intended to capture both external mediation and internal feedback based on our prior neural decoding experience and grid-cell inspiration. We will revise the abstract to state explicitly that the self-reinforcement is a hypothesized property of the framework rather than an independently benchmarked result, and we will add a paragraph in the introduction tracing the SD2E rules to specific observations from the cited experiments. revision: yes

  2. Referee: [System description] System description (throughout): No mathematical derivations, equations, pseudocode, or algorithmic specification is given for how the grid produces 0/1 signals, how the space-division (SD) module processes them, or how exploration-exploitation is implemented within the Bayesian framework. This absence is load-bearing because the manuscript positions the system as a general and robust construction capable of the stated functions.

    Authors: We acknowledge that the absence of explicit specifications limits evaluability. Although the work is framed as a high-level theoretical model, we will add a new subsection containing pseudocode for grid 0/1 signal generation, SD module processing of those signals, and the Bayesian update steps governing exploration-exploitation. This will supply the algorithmic detail requested while preserving the conceptual emphasis of the paper. revision: yes

  3. Referee: [Rationality analysis] Rationality analysis section: The analysis of the system's rationality against existing neuroscience and cognitive science theories remains at a high conceptual level without specific model comparisons, quantitative contrasts, or demonstrations that Grid-SD2E resolves documented limitations in prior frameworks.

    Authors: The current analysis is intentionally conceptual to synthesize ideas across fields. We will expand the section with targeted comparisons, for example contrasting Grid-SD2E's grid-feedback loop against standard Bayesian cognitive models that lack an equivalent internal reinforcement mechanism, and we will cite documented integration difficulties in prior frameworks that the proposed dual-role grid module is intended to mitigate. Quantitative contrasts remain outside the present theoretical scope. revision: partial

Circularity Check

0 steps flagged

Theoretical framework with no derivation chain or self-referential reductions

full rationale

The manuscript is explicitly a high-level conceptual proposal for a Grid-SD2E system, positioned as inspired by external grid-cell experiments and prior neural-decoding experience. It states that the system 'is also a theoretical model derived from experiments conducted by other researchers' and proceeds to 'analyse the rationality of the system based on the existing theories in both neuroscience and cognitive science.' No equations, fitted parameters, or formal derivations appear; the smallest-computing-unit extraction is described only as an extraction 'based on this framework.' Because no load-bearing step reduces by construction to an internal definition, self-citation, or fitted input, the paper contains no circularity of the enumerated kinds.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 2 invented entities

The central claim rests on domain assumptions drawn from neuroscience and cognitive science plus newly introduced entities whose only support is the proposal itself.

axioms (2)
  • domain assumption Grid cells can be generalized into a module that serves both external interaction and internal self-reinforcement
    Stated in abstract as inspiration from grid cells
  • domain assumption Bayesian reasoning integrates with SD2E to produce self-reinforcing cognitive learning
    Stated in abstract as part of the system construction
invented entities (2)
  • Grid module as dual interaction and self-reinforcement medium no independent evidence
    purpose: To act as medium between outside world and system and within the system
    Newly defined for the Grid-SD2E framework
  • Smallest computing unit analogous to a single neuron no independent evidence
    purpose: Extracted from the framework as basic unit
    Proposed at end of abstract

pith-pipeline@v0.9.0 · 5768 in / 1462 out tokens · 36034 ms · 2026-05-24T09:06:54.404788+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

80 extracted references · 80 canonical work pages · 4 internal anchors

  1. [1]

    N. Wiener. Cybernetics: or the Control and Communication in the Animal and the Machine. Peking University Press, 2020

    work page 2020

  2. [2]

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

    work page 1950

  3. [3]

    J.V . Neumann. The Computer and the Brain. Yale University Press, 2012

    work page 2012

  4. [4]

    Wallisch, M.E

    P. Wallisch, M.E. Lusignan, M.D. Benayoun, Baker T.I., A.S. Dickey, and N.G. Hatsopoulos.MATLAB for neuroscientists: an introduction to scientific computing in MATLAB. Academic Press, 2014

    work page 2014

  5. [5]

    Livezey and J.I

    J.A. Livezey and J.I. Glaser. Deep learning approaches for neural decoding: from cnns to lstms and spikes to fmri. Briefings in Bioinformatics, 22(2):1577–1591, 2021

    work page 2021

  6. [6]

    A. Clark. Surfing Uncertainty: Prediction, Action, and the Embodied Mind. OUP USA, 2016

    work page 2016

  7. [7]

    Friston, J

    K.J. Friston, J. Daunizeau, J. Kilner, and S.J. Kiebel. Action and behavior: a free-energy formulation. Biological Cybernetics, 102(3):227–260, 2010

    work page 2010

  8. [8]

    Ramstead, P.B

    D.M.J. Ramstead, P.B. Badcock, and K.J. Friston. Answering schrödinger’s question: A free-energy formulation. Physics of Life Reviews, 24:1–16, 2018

    work page 2018

  9. [9]

    Hawkins and S

    J. Hawkins and S. Blakeslee. On Intelligence: How a New Understanding of the Brain will Lead to the Creation of Truly Intelligent Machines. Times Books, 2004

    work page 2004

  10. [10]

    Hawkins, M

    J. Hawkins, M. Lewis, M. Klukas, S. Purdy, and S. Ahmad. A framework for intelligence and cortical function based on grid cells in the neocortex. Frontiers in Neural Circuits, 12:DOI=10.3389/fncir.2018.00121, 2019

    work page doi:10.3389/fncir.2018.00121 2018

  11. [11]

    J. Hawkins. A Thousand Brains: A New Theory of Intelligence. Basic Books, 2021

    work page 2021

  12. [12]

    Nagel, J.R

    E. Nagel, J.R. Newman, and D.R. Hofstadter. Gödel’s Proof: Revised Edition. NYU Press, 2001

    work page 2001

  13. [13]

    Hofstadter

    D.R. Hofstadter. Gödel, Escher, Bach: An Eternal Golden Braid. Basic Books, 1999

    work page 1999

  14. [14]

    Hofstadter

    D.R. Hofstadter. I Am a Strange Loop. Basic Books, 2007

    work page 2007

  15. [15]

    Hofstadter and E

    D.R. Hofstadter and E. Sander. Surfaces and Essences: Analogy as the Fuel and Fire of Thinking. Basic Books, 2013

    work page 2013

  16. [16]

    Goodfellow, Y

    I. Goodfellow, Y . Bengio, and A. Courville.Deep Learning: Adaptive Computation and Machine Learning series. The MIT Press, 2016

    work page 2016

  17. [17]

    Bengio, Y

    Y . Bengio, Y . Lecun, and Hinton G. Deep learning for AI.Communications of the ACM, 64(7):58–65, 2021

    work page 2021

  18. [18]

    Sutton and A.G

    R.S. Sutton and A.G. Barto. Reinforcement Learning: An Introduction (second edition). A Bradford Book, 2018

    work page 2018

  19. [19]

    R.S. Sutton. The quest for a common model of the intelligent decision maker. arXiv preprint arXiv:2202.13252v2, 2022

    work page arXiv 2022

  20. [20]

    H.F. Wu, J.Y . Feng, and Y . Zeng. Neural decoding for macaque’s finger position: Convolutional space model.IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27(3):543–551, 2019

    work page 2019

  21. [21]

    Feng, H.F

    J.Y . Feng, H.F. Wu, and Y . Zeng. Neural decoding for location of macaque’s moving finger using generative adversarial networks. In IEEE International Conference of Intelligent Robotic and Control Engineering, pages 213–217. IEEE, 2018

    work page 2018

  22. [24]

    Friston, T

    K. Friston, T. Parr, and B. de Vries. The graphical brain: Belief propagation and active inference. Network Neuroscience, 1(4):381–414, 2017

    work page 2017

  23. [25]

    Friston, T

    K. Friston, T. FitzGerald, F. Rigoli, P. Schwartenbeck, and G. Pezzulo. Active inference: A process theory.Neural Computation, 29(1):1–49, 2017. 15 Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning (Neural Decoding)

    work page 2017

  24. [26]

    H. Attias. Planning by probabilistic inference. Proc. of the 9th Int. Workshop on Artificial Intelligence and Statistics, 2003

    work page 2003

  25. [27]

    Botvinick and M

    M. Botvinick and M. Toussaint. Planning as inference. Trends in Cognitive Sciences, 16(10):485–488, 2012

    work page 2012

  26. [28]

    Da Costa, T

    L. Da Costa, T. Parr, N. Sajid, S. Veselic, V . Neacsu, and K. Friston. Active inference on discrete state-spaces: A synthesis. Journal of Mathematical Psychology, 99:102447, 2020

    work page 2020

  27. [29]

    Lanillos, C

    P. Lanillos, C. Meo, C. Pezzato, A.A. Meera, M. Baioumy, W. Ohata, A. Tschantz, B. Millidge, M. Wisse, C.L. Buckley, and J. Tani. Active inference in robotics and artificial agents: Survey and challenges. arXiv preprint arXiv:2112.01871, 2021

    work page arXiv 2021

  28. [30]

    Hafting, M

    T. Hafting, M. Fyhn, S. Molden, M.B. Moser, and E.I. Moser. Microstructure of a spatial map in the entorhinal cortex. Nature, 436(7052):801–806, 2005

    work page 2005

  29. [31]

    Milford, G.F

    M.J. Milford, G.F. Wyeth, and D. Prasser. Ratslam: a hippocampal model for simultaneous localization and mapping. In IEEE International Conference on Robotics and Automation, 2004. Proceedings. ICRA ’04. 2004, pages 403–408. IEEE, 2004

    work page 2004

  30. [32]

    F. Yu, J. Shang, Y . Hu, and M. Milford. Neuroslam: a brain-inspired slam system for 3d environments.Biological Cybernetics, 113:515–545, 2019

    work page 2019

  31. [33]

    Moser, Y

    E.I. Moser, Y . Roudi, M.P. Witter, C. Kentros, T. Bonhoeffer, and M.B. Moser. Grid cells and cortical representation.Nature Reviews Neuroscience, 15:466–481, 2014

    work page 2014

  32. [34]

    O’Keefe and J

    j. O’Keefe and J. Dostrovsky. The hippocampus as a spatial map. preliminary evidence from unit activity in the freely-moving rat. Brain Research, 34(1):171–175, 1971

    work page 1971

  33. [35]

    Taube, R.U

    J.S. Taube, R.U. Muller, and J.B.Jr Ranck. Head-direction cells recorded from the postsubiculum in freely moving rats. i. description and quantitative analysis. Journal of Neuroscience, 10(2):420–435, 1990

    work page 1990

  34. [36]

    Lever, S

    C. Lever, S. Burton, A. Jeewajee, J. O’Keefe, and N. Burgess. Boundary vector cells in the subiculum of the hippocampal formation. Journal of Neuroscience, 29(31):9771–9777, 2009

    work page 2009

  35. [37]

    Barry, R

    C. Barry, R. Hayman, N. Burgess, and Jeffery K.J. Experience-dependent rescaling of entorhinal grids. Nature Neuroscience, 10:682–684, 2007

    work page 2007

  36. [38]

    Stensola, T

    H. Stensola, T. Stensola, T. Solstad, K. Frøland, M.B. Moser, and Moser E.I. The entorhinal grid map is discretized. Nature, 492:72–78, 2012

    work page 2012

  37. [39]

    Stensola, H

    T. Stensola, H. Stensola, M.B. Moser, and Moser E.I. Shearing-induced asymmetry in entorhinal grid cells. Nature, 518:207– 212, 2015

    work page 2015

  38. [40]

    L.M. Giocomo. Spatial representation: Maps of fragmented space. Current Biology, 25(9):R362–R363, 2015

    work page 2015

  39. [41]

    Ginosar, J

    G. Ginosar, J. Aljadeff, Y . Burak, H. Sompolinsky, L. Las, and Ulanovsky N. Locally ordered representation of 3d space in the entorhinal cortex. Nature, 596:404–409, 2021

    work page 2021

  40. [42]

    Grieves, S

    R.M. Grieves, S. Jedidi-Ayoub, K. Mishchanchuk, A. Liu, S. Renaudineau, É. Duvelle, and K.J. Jeffery. Irregular distribution of grid cell firing fields in rats exploring a 3d volumetric space. Nature Neuroscience, 24:1567–1573, 2021

    work page 2021

  41. [43]

    J. Hohwy. The self-evidencing brain. Noûs, 50(2):259–285, 2014

    work page 2014

  42. [44]

    E.T. Jaynes. Information theory and statistical mechanics. Physical Review Series II, 106(4):620–630, 1957

    work page 1957

  43. [45]

    Schmidhuber

    J. Schmidhuber. Curious model-building control systems. In Proc. International Joint Conference on Neural Networks , 2:1458–1463, 1991

    work page 1991

  44. [46]

    Schmidhuber

    J. Schmidhuber. Formal theory of creativity, fun, and intrinsic motivation (1990-2010). IEEE Transactions on Autonomous Mental Development, 2(3):230–247, 2010

    work page 1990

  45. [47]

    Y . Sun, F. Gomez, and J. Schmidhuber. Planning to be surprised: optimal bayesian exploration in dynamic environments. Proceedings of the 4th international conference on Artificial general intelligence, pages 41–51, 2011

    work page 2011

  46. [48]

    D.J. MacKay. Free-energy minimisation algorithm for decoding and cryptoanalysis. Electronics Letters, 31:445–447, 1995

    work page 1995

  47. [49]

    Wallace and D.L

    C.S. Wallace and D.L. Dowe. Minimum message length and kolmogorov complexity. The Computer Journal, 42(4):270–283, 1999

    work page 1999

  48. [50]

    Schrödinger

    E. Schrödinger. What is life? Cambridge University Press, 1944

    work page 1944

  49. [51]

    K. Gödel. Über formal unentscheidbare sätze der principia mathematica und verwandter systeme i.Monatshefte für Mathematik, 38(1):173–198, 1931

    work page 1931

  50. [52]

    J. Pearl. Causality: Models, Reasoning and Inference. Cambridge University Pressence, 2009

    work page 2009

  51. [53]

    Pearl and D

    J. Pearl and D. Mackenzie. The Book of Why: The New Science of Cause and Effect. Basic Books, 2018

    work page 2018

  52. [54]

    Y . Liu. Integrated human-machine intelligence: beyond artificial intelligence. Tsing Hua University Press, 2021

    work page 2021

  53. [55]

    World Models

    D. Ha and J. Schmidhuber. World models. arXiv preprint arXiv:1803.10122v4, 2018

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  54. [56]

    Friston, R.J

    K. Friston, R.J. Moran, Y . Nagai, T. Taniguchi, H. Gomi, and J. Tenenbaum. World model learning and inference. Neural Networks, 144:573–590, 2021

    work page 2021

  55. [57]

    Y . LeCun. A path towards autonomous machine intelligence. https://openreview.net/pdf?id=BZ5a1r-kVsf, 2022. 16 Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning (Neural Decoding)

    work page 2022

  56. [58]

    Wang and B

    P. Wang and B. Goertzel. Introduction: Aspects of artificial general intelligence. in Advance of Artificial General Intelligence, pages 1–16, 2007

    work page 2007

  57. [59]

    Zador, S

    A. Zador, S. Escola, B. Richards, B. Ölveczky, Y . Bengio, K. Boahen, M. Botvinick, D. Chklovskii, A. Churchland, C. Clopath, J. DiCarlo, S. Ganguli, J. Hawkins, K. Körding, A. Koulakov, Y . LeCun, T. Lillicrap, A. Marblestone, B. Olshausen, A. Pouget, C. Savin, T. Sejnowski, E. Simoncelli, S. Solla, D. Sussillo, A.S. Tolias, and D. Tsao. Catalyzing next-...

    work page 2023

  58. [60]

    F. Chollet. On the measure of intelligence. arXiv preprint arXiv:1911.01547, 2019

    work page internal anchor Pith review Pith/arXiv arXiv 1911

  59. [61]

    G. Hinton. The forward-forward algorithm: Some preliminary investigations. arXiv preprint arXiv:2212.13345v1, 2022

    work page arXiv 2022

  60. [62]

    Cognitive physics—the enlightenment by schrödinger, turing, and wiener and beyond

    D.Y Li. Cognitive physics—the enlightenment by schrödinger, turing, and wiener and beyond. Intelligent computing, 2, 2023

    work page 2023

  61. [63]

    Consciousness in Artificial Intelligence: Insights from the Science of Consciousness

    P. Butlin, R. Long, E. Elmoznino, Y . Bengio, J. Birch, A. Constant, G. Deane, S.M. Fleming, C. Frith, X. Ji, R. Kanai, C. Klein, G. Lindsay, M. Michel, L. Mudrik, M.A.K. Peters, E. Schwitzgebel, J. Simon, and VanRullen R. Consciousness in artificial intelligence: Insights from the science of consciousness. arXiv preprint arXiv:2308.08708v3, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  62. [64]

    Oizumi, L

    M. Oizumi, L. Albantakis, and G. Tononi. From the phenomenology to the mechanisms of consciousness: Integrated information theory 3.0. PLOS Computational Biology, 2014

    work page 2014

  63. [65]

    Tononi and C

    G. Tononi and C. Koch. Consciousness: here, there and everywhere? Philosophical Transactions of the Royal Society B: Biological Sciences, 2015

    work page 2015

  64. [66]

    Albantakis and G

    L. Albantakis and G. Tononi. What we are is more than what we do. arXiv preprint arXiv:2102.04219v1, 2021

    work page arXiv 2021

  65. [67]

    Michel and H

    M. Michel and H. Lau. On the dangers of conflating strong and weak versions of a theory of consciousness. Philosophy and the Mind Sciences, 2020

    work page 2020

  66. [68]

    Mediano, F.E

    P.A.M. Mediano, F.E. Rosas, D. Bor, A.K. Seth, and A.B. Barrett. The strength of weak integrated information theory. Trends in Cognitive Sciences, 26(8):646–655, 2022

    work page 2022

  67. [69]

    Anthropic Bias : Observation Selection Effects in Science and Philosophy

    Bostrom N. Anthropic Bias : Observation Selection Effects in Science and Philosophy. Psychology Press, 2002

    work page 2002

  68. [70]

    Marcus and E Davis

    G. Marcus and E Davis. Insights for ai from the human mind. Communications of the ACM, 64(1):38–41, 2021

    work page 2021

  69. [71]

    Lenat D. and G. Marcus. Getting from generative ai to trustworthy ai: What llms might learn from cyc. arXiv preprint arXiv:2308.04445v1, 2023

    work page arXiv 2023

  70. [72]

    L.N. Hoang. La formule du savoir: Une philosophie unifiée du savoir fondée sur le théorème de Bayes. XXX, 2018

    work page 2018

  71. [73]

    Marr and S

    D. Marr and S. Ullman. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information. The MIT Press, 2010

    work page 2010

  72. [74]

    Hatch and H

    T. Hatch and H. Gardner. Finding Cognition in the Classroom: an Expanded View of Human Intelligence. New York: Press Syndicate of the University of Cambridge, 1993

    work page 1993

  73. [75]

    Hutchins

    E. Hutchins. Cognition in the Wild. MIT Press, 1995

    work page 1995

  74. [76]

    G.F. Marcus. The Algebraic Mind: Integrating Connectionism and Cognitive Science (Learning, Development, and Conceptual Change). The MIT Press, 2003

    work page 2003

  75. [77]

    Mitchell

    M. Mitchell. Artificial Intelligence: A Guide for Thinking Humans. Pelican, 2019. 17 Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning (Neural Decoding) Galton board Algorithm board Un-al Data Nail Ball substance code 2 2 1 ( )( ) exp( ) 22 xfx   −=− (a) Galton board (b) Algorithm board ()( ) ( ) () p data | hypothesisp hypothesis ...

    work page 2019

  76. [78]

    Feng, H.F

    J.Y . Feng, H.F. Wu, and Y . Zeng. Neural decoding for location of macaque’s moving finger using generative adversarial networks. In IEEE International Conference of Intelligent Robotic and Control Engineering, pages 213—217. IEEE, 2018

    work page 2018

  77. [79]

    Feng, H.F

    J.Y . Feng, H.F. Wu, Y . Zeng, and Y .H. Wang. Weakly supervised learning in neural encoding for the position of the moving finger of a macaque. Cognitive Computation, 12(5):1083–1096, 2020

    work page 2020

  78. [80]

    J.Y . Feng, Y . Luo, and S. Song. ViF-SD2E: A robust weakly-supervised method for neural decoding. arXiv preprint arXiv:2112.01261v3, 2021–2022. vs. (Final Version). J.Y . Feng, Y . Luo, S. Song, and H. Hu. ViF-SD2E: A robust weakly-supervised framework for neural decoding. Under review, 2023

    work page arXiv 2021

  79. [81]

    Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning

    J.Y . Feng, and C.M. Zhang. Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning.arXiv preprint arXiv:2304.01844v3, 2023–2024. Under review, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  80. [82]

    grid module,

    J.Y . Feng, Y . Luo, and K. Yang. From a symmetry discovered in neural decoding to an algorithm board.Under review, 2024. 18 Grid-SD2E: A General Grid-Feedback in a System for Cognitive Learning (Neural Decoding) Note: The cups and fragments, these pictures are made by Bing Image Creator and powered by DALL.E. Slide 59 MI=BI: Two cognitive paradigms of sc...

    work page 2024