pith. sign in

arxiv: 2604.13829 · v1 · submitted 2026-04-15 · 💻 cs.OH

Use and usability: concepts of representation in philosophy, neuroscience, cognitive science, and computer science

Ben Baker , Richard D. Lange , Andrew Richmond , Nikolaus Kriegeskorte , Rosa Cao , Xaq Pitkow , Odelia Schwartz This is my paper

Pith reviewed 2026-05-10 12:31 UTC · model grok-4.3

classification 💻 cs.OH
keywords representationusabilityneural representationsinformationneurosciencephilosophycognitive sciencecomputer science
0
0 comments X

The pith

Representations are understood at three levels based on whether their information is useful, in usable format, and actually used.

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

The paper reviews how usefulness factors into conceptions of representation across philosophy, neuroscience, cognitive science, and computer science. It breaks down use into four aspects: carrying information, that information being useful, the format being usable, and the representation being used downstream. These aspects allow organizing perspectives into three levels of increasing engagement with use. A reader would care because this provides a way to navigate inconsistent uses of the term representation in studies of intelligence.

Core claim

Building on four aspects of information and use, existing perspectives on neural representations are organized into three levels: Representations as Information (Level 1); Representations as Usable (Level 2); and Representations as Used (Level 3). The account helps appreciate the diversity of notions of neural representation and clarify the appropriate notion for specific investigations.

What carries the argument

The taxonomy of three levels of representation supported by the four aspects of information, usefulness, usable format, and downstream use.

If this is right

  • Studies of neural codes can be classified by whether they address mere information presence or actual usability.
  • Models in AI can be evaluated on which level of representation they implement.
  • Philosophical arguments about representation can be mapped to these levels to resolve apparent disagreements.
  • Investigators can choose the level appropriate to their research question to avoid mismatch.

Where Pith is reading between the lines

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

  • This organization could reveal gaps in current research where certain levels are understudied.
  • It might suggest new experiments that test the transition from usable to used representations.
  • Connecting to neighboring problems like the role of representations in learning or decision making could extend the framework.

Load-bearing premise

The four aspects comprehensively capture the relevant dimensions of representation across the disciplines without significant omissions.

What would settle it

Discovery of a conception of representation in one of the fields that fits none of the three levels or requires a fifth aspect of use.

read the original abstract

Representations play a central role in the study of both biological and artificial intelligence, as well as philosophy of mind. Across neuroscience, computer science, and philosophy, a recurring theme is that representations not only carry information but should be ``useful'' for or ``usable'' by an agent in some sense. Here, we review how the ``usefulness'' of representations has been conceptualized and how it figures into different conceptions of representation. We identify and explore four aspects of use and usability: representations generally carry \textit{information}; that information may or may not be \textit{useful} and it may or may not be encoded in a usable \textit{format}; and the representations may or may not be \textit{used downstream}. Building on these four aspects of information and use, we then organize existing perspectives on neural representations into three levels: Representations as Information (Level 1); Representations as Usable (Level 2); and Representations as Used (Level 3). Our account is meant to give readers an appreciation for the diversity of notions of ``neural representation,'' help them navigate the vast and multi-disciplinary literature on the topic, and help them clarify the appropriate notion of representation for their own investigations.

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

0 major / 2 minor

Summary. The manuscript reviews how usefulness and usability figure into conceptions of representation across philosophy, neuroscience, cognitive science, and computer science. It identifies four aspects—representations carry information; that information may or may not be useful; it may or may not be encoded in a usable format; and representations may or may not be used downstream—and employs these to organize existing perspectives on neural representations into three levels: Representations as Information (Level 1), Representations as Usable (Level 2), and Representations as Used (Level 3). The account is intended to help readers appreciate the diversity of notions and navigate the multidisciplinary literature.

Significance. If the taxonomy holds, the paper supplies a coherent organizational framework for a sprawling interdisciplinary topic without introducing new parameters, axioms, or empirical claims. Its value lies in the explicit linkage of the four aspects to the three levels and the cross-field synthesis, which can assist researchers in selecting defensible notions of representation for their own work. The absence of self-referential derivations or fitted quantities is a strength for a review of this type.

minor comments (2)
  1. A summary table mapping the four aspects to the three levels, with one or two canonical citations per cell, would improve readability and make the organizational claim easier to apply.
  2. The manuscript should explicitly note any disciplinary literatures (e.g., embodied cognition or social epistemology) that fall outside the four-aspect framing, even if only to delimit scope.

Simulated Author's Rebuttal

0 responses · 0 unresolved

We thank the referee for their positive assessment of the manuscript, including the recognition of its value as a cross-disciplinary organizational framework for notions of neural representation. We appreciate the recommendation for minor revision and note that no specific major comments were raised in the report.

Circularity Check

0 steps flagged

No significant circularity in this conceptual review and taxonomy

full rationale

This paper is a review and synthesis that identifies four aspects of representation (information carried, usefulness, usable format, downstream use) drawn from existing multi-disciplinary literature and uses them to organize prior perspectives into three levels. The central contribution is the coherence and utility of this framing rather than any derivation, model, or empirical claim. No equations, fitted parameters, or self-citation chains appear; the argument rests on external citations and does not reduce any claim to its own inputs by construction. This is the expected non-finding for a self-contained organizational review.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The paper rests on standard domain assumptions about the role of representations in intelligence and mind; no new free parameters or invented entities are introduced.

axioms (1)
  • domain assumption Representations carry information that can be evaluated for usefulness and usability.
    Stated directly in the abstract as a recurring theme across fields.

pith-pipeline@v0.9.0 · 5538 in / 967 out tokens · 41042 ms · 2026-05-10T12:31:53.108873+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

166 extracted references · 166 canonical work pages

  1. [1]

    Fallon FT, Ryan TJ, Krakauer JW, What Are We T alking about? Clarifying the Fuzzy Concept of Representation in Neuroscience and Beyond; 2023

    work page 2023

  2. [2]

    Three Aspects of Representation in Neuroscience

    Baker B, Lansdell B, Kording KP . Three Aspects of Representation in Neuroscience. T rends in Cognitive Sciences 2022 Nov;26(11):942–958

    work page 2022

  3. [3]

    Investigating the Concept of Representation in the Neural and Psychological Sciences

    Favela LH, Machery E. Investigating the Concept of Representation in the Neural and Psychological Sciences. Frontiers in Psychology 2023 Jun;14:1–13

    work page 2023

  4. [4]

    Commentary: Investigating the Concept of Representation in the Neural and Psychological Sciences

    Richmond A. Commentary: Investigating the Concept of Representation in the Neural and Psychological Sciences. Frontiers in Psychology 2023;14

    work page 2023

  5. [5]

    Putting Representations to Use

    Cao R. Putting Representations to Use. Synthese 2022 Apr;200(2):151

    work page 2022

  6. [6]

    Deflating Mental Representation

    Egan F . Deflating Mental Representation. The Jean Nicod Lectures, Cambridge, Massachusetts: The MIT Press; 2025

    work page 2025

  7. [7]

    The Extended Mind

    Clark A, Chalmers D. The Extended Mind. Analysis 1998;58(1):7–19

    work page 1998

  8. [8]

    The Embodied Mind: Cognitive Science and Human Experience

    Varela FJ, Thompson E, Rosch E. The Embodied Mind: Cognitive Science and Human Experience. 14. print. ed. Cam- bridge, Mass.: MIT Press; 1993

    work page 1993

  9. [9]

    Untangling Invariant Object Recognition

    DiCarlo JJ, Cox DD. Untangling Invariant Object Recognition. T rends in Cognitive Sciences 2007;11(8):333–341

    work page 2007

  10. [10]

    Interpreting Encoding and Decoding Models

    Kriegeskorte N, Douglas PK. Interpreting Encoding and Decoding Models. Current Opinion in Neurobiology 2019 Apr;55:167–179

    work page 2019

  11. [11]

    arXiv; 2022

    Ivanova AA, Schrimpf M, Anzellotti S, Zaslavsky N, Fedorenko E, Isik L, Beyond Linear Regression: Mapping Models in Cognitive Neuroscience Should Align with Research Goals. arXiv; 2022

    work page 2022

  12. [12]

    Representation Learning: A Review and New Perspectives

    Bengio Y, Courville A, Vincent P . Representation Learning: A Review and New Perspectives. IEEE T ransactions on Pattern Analysis and Machine Intelligence 2013;35(8):1798–1828

    work page 2013

  13. [13]

    A Framework for the Quantitative Evaluation of Disentangled Representations

    Eastwood C, Williams CKI. A Framework for the Quantitative Evaluation of Disentangled Representations. ICLR 2018

    work page 2018

  14. [14]

    T owards a Definition of Disentangled Represen- tations

    Higgins I, Amos D, Pfau D, Racaniere S, Matthey L, Rezende D, et al. T owards a Definition of Disentangled Represen- tations. arXiv 2018;p. 1–29

    work page 2018

  15. [15]

    Deep Learning and the Information Bottleneck Principle

    Tishby N, Zaslavsky N. Deep Learning and the Information Bottleneck Principle. arXiv 2015

    work page 2015

  16. [16]

    Emergence of Invariance and Disentanglement in Deep Representations

    Achille A, Soatto S. Emergence of Invariance and Disentanglement in Deep Representations. Information Theory and Applications Workshop 2018;19:1–34

    work page 2018

  17. [17]

    Clarifying the Conceptual Dimensions of Representation in Neuroscience

    Pohl S, Walker EY, Barack DL, Lee J, Denison RN, Block N, et al. Clarifying the Conceptual Dimensions of Representation in Neuroscience. Nature Reviews Neuroscience 2026 Mar;p. 1–16

    work page 2026

  18. [18]

    Grounded Cognition: Past, Present, and Future

    Barsalou LW. Grounded Cognition: Past, Present, and Future. T opics in Cognitive Science 2010 Oct;2(4):716–724

    work page 2010

  19. [19]

    The Modal—Amodal Distinction in the Debate on Conceptual Format

    Haimovici S. The Modal—Amodal Distinction in the Debate on Conceptual Format. Philosophies 2018 Jun;3(2):7–19

    work page 2018

  20. [20]

    Grounding Action Representations

    Weber AM, Vosgerau G. Grounding Action Representations. Review of Philosophy and Psychology 2012 Mar;3(1):53– 69

    work page 2012

  21. [21]

    Representation Reconsidered

    Ramsey W. Representation Reconsidered. Cambridge: Cambridge University Press; 2007

    work page 2007

  22. [22]

    arXiv; 2018

    Alain G, Bengio Y, Understanding Intermediate Layers Using Linear Classifier Probes. arXiv; 2018. 26 Baker, Lange, Richmond et al

    work page 2018

  23. [23]

    Fast Readout of Object Identity from Macaque Inferior T emporal Cortex

    Hung CP , Kreiman G, Poggio T, DiCarlo JJ. Fast Readout of Object Identity from Macaque Inferior T emporal Cortex. Science 2005 Nov;310(5749):863–866

    work page 2005

  24. [24]

    Decoding the Brain: Neural Representation and the Limits of Multivariate Pattern Analysis in Cognitive Neuroscience

    Ritchie JB, Kaplan DM, Klein C. Decoding the Brain: Neural Representation and the Limits of Multivariate Pattern Analysis in Cognitive Neuroscience. The British Journal for the Philosophy of Science 2019 Jun;70(2):581–607

    work page 2019

  25. [25]

    Representational Models: A Common Framework for Understanding Encoding, Pattern- Component, and Representational-Similarity Analysis, vol

    Diedrichsen J, Kriegeskorte N. Representational Models: A Common Framework for Understanding Encoding, Pattern- Component, and Representational-Similarity Analysis, vol. 13; 2017

    work page 2017

  26. [26]

    What Representational Similarity Measures Imply about Decodable Information

    Harvey SE, Lipshutz D, Williams AH. What Representational Similarity Measures Imply about Decodable Information. In: UniReps: 2nd Edition of the Workshop on Unifying Representations in Neural Models; 2024

    work page 2024

  27. [27]

    Peeling the Onion of Brain Representations

    Kriegeskorte N, Diedrichsen J. Peeling the Onion of Brain Representations. Annual Review of Neuroscience 2019;42:407–432

    work page 2019

  28. [28]

    Decoding the Cognitive Map: Ensemble Hippocampal Sequences and Decision Making

    Wikenheiser AM, Redish AD. Decoding the Cognitive Map: Ensemble Hippocampal Sequences and Decision Making. Current Opinion in Neurobiology 2015 Jun;32:8–15

    work page 2015

  29. [29]

    Neuroscience Needs Behavior: Correcting a Reductionist Bias

    Krakauer JW, Ghazanfar AA, Gomez-Marin A, Maciver MA, Poeppel D. Neuroscience Needs Behavior: Correcting a Reductionist Bias. Neuron Perspective 2017;93(3):480–490

    work page 2017

  30. [30]

    Contents, Vehicles, and Complex Data Analysis in Neuroscience

    Burnston DC. Contents, Vehicles, and Complex Data Analysis in Neuroscience. Synthese An International Journal for Epistemology, Methodology and Philosophy of Science 2020;199:1617–1639

    work page 2020

  31. [31]

    Single-T rial Neural Dynamics Are Dominated by Richly Varied Movements

    Musall S, Kaufman MT, Juavinett AL, Gluf S, Churchland AK. Single-T rial Neural Dynamics Are Dominated by Richly Varied Movements. Nature Neuroscience 2019 Oct;22(10):1677–1686

    work page 2019

  32. [32]

    Context-Dependent Computation by Recurrent Dynamics in Prefrontal Cortex

    Mante V, Sussillo D, Shenoy KV, Newsome WT. Context-Dependent Computation by Recurrent Dynamics in Prefrontal Cortex. Nature 2013;503(7474):78–84

    work page 2013

  33. [33]

    What Is a Theory of Neural Representation For? Synthese An International Journal for Epistemology, Methodology and Philosophy of Science 2025;205(14)

    Richmond A. What Is a Theory of Neural Representation For? Synthese An International Journal for Epistemology, Methodology and Philosophy of Science 2025;205(14)

    work page 2025

  34. [34]

    Multitask Learning

    Caruana R. Multitask Learning. Machine Learning 1997 Jul;28(1):41–75

    work page 1997

  35. [35]

    Exploiting T ask Relatedness for Multiple T ask Learning

    Ben-David S, Schuller R. Exploiting T ask Relatedness for Multiple T ask Learning. In: Goos G, Hartmanis J, Van Leeuwen J, Schölkopf B, Warmuth MK, editors. Learning Theory and Kernel Machines, vol. 2777 Berlin, Heidelberg: Springer Berlin Heidelberg; 2003.p. 567–580

    work page 2003

  36. [36]

    Examples of Gibsonian Affordances in Legged Robotics Research Using an Empirical, Generative Framework

    Roberts SF, Koditschek DE, Miracchi LJ. Examples of Gibsonian Affordances in Legged Robotics Research Using an Empirical, Generative Framework. Frontiers in Neurorobotics 2020;14(February)

    work page 2020

  37. [37]

    The Affordance Competition Hypothesis: A Framework for Embodied Behavior

    Cisek P . The Affordance Competition Hypothesis: A Framework for Embodied Behavior. In: Klatzky RL, MacWhinney B, Behrmann M, editors. Embodiment, Ego-Space, and Action, 0 ed. Psychology Press; 2008

    work page 2008

  38. [38]

    arXiv; 2019

    Frankle J, Carbin M, The Lottery Ticket Hypothesis: Finding Sparse, T rainable Neural Networks. arXiv; 2019

    work page 2019

  39. [39]

    T emporal Structure of Motor Variability Is Dynamically Regulated and Predicts Motor Learning Ability

    Wu HG, Miyamoto YR, Castro LNG, Ölveczky BP , Smith MA. T emporal Structure of Motor Variability Is Dynamically Regulated and Predicts Motor Learning Ability. Nature Neuroscience 2014;17(2):312–321

    work page 2014

  40. [40]

    Neural Spiking for Causal Inference and Learning

    Lansdell BJ, Kording KP . Neural Spiking for Causal Inference and Learning. PLOS Computational Biology 2023 Apr;19(4):e1011005

    work page 2023

  41. [41]

    The Information Bottleneck Method

    Tishby N, Pereira FC, Bialek W. The Information Bottleneck Method. Proceedings of the 37th Allerton Conference on Communication, Control, and Computing 1999;p. 368–377

    work page 1999

  42. [42]

    Visual Representations: Defining Properties and Deep Approximations

    Soatto S, Chiuso A. Visual Representations: Defining Properties and Deep Approximations. ICLR 2016;p. 1–20. Baker, Lange, Richmond et al. 27

    work page 2016

  43. [43]

    Natural Image Statistics and Neural Representation

    Simoncelli EP , Olshausen BA. Natural Image Statistics and Neural Representation. Annual Review of Neuroscience 2001 Mar;24(Volume 24, 2001):1193–1216

    work page 2001

  44. [44]

    Efficient Representation as a Design Principle for Neural Coding and Computation

    Bialek W, de Ruyter van Stevenick RR, Tishby N. Efficient Representation as a Design Principle for Neural Coding and Computation. IEEE International Symposium on Information Theory 2007;p. 659–663

    work page 2007

  45. [45]

    Sparse Coding with an Incomplete Basis Set: A Strategy Employed by V1? Vision Research 1997;37(23):3311–3325

    a Olshausen B, Field DJ. Sparse Coding with an Incomplete Basis Set: A Strategy Employed by V1? Vision Research 1997;37(23):3311–3325

    work page 1997

  46. [46]

    Possible Principles Underlying the T ransformations of Sensory Messages

    Barlow HB. Possible Principles Underlying the T ransformations of Sensory Messages. Sensory Communication 1961;p. 216–234

    work page 1961

  47. [47]

    Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems

    Dayan P , Abbott LF . Theoretical Neuroscience: Computational and Mathematical Modeling of Neural Systems. Se- jnowski TJ, Poggio T, editors, London: MIT Press; 2001

    work page 2001

  48. [48]

    T oward a Unified Theory of Efficient, Predictive, and Sparse Coding

    Chalk M, Marre O, Tkačik G. T oward a Unified Theory of Efficient, Predictive, and Sparse Coding. Proceedings of the National Academy of Sciences 2018;115(1):186–191

    work page 2018

  49. [49]

    The Foundations of Statistics

    Savage LJ. The Foundations of Statistics. Courier Corporation; 1972

    work page 1972

  50. [50]

    Decision Theory: What "Should" the Nervous System Do? Science 2008;606(2007)

    Körding KP . Decision Theory: What "Should" the Nervous System Do? Science 2008;606(2007)

    work page 2008

  51. [51]

    Probabilistic Interpretation of Population Codes

    Zemel RS, Dayan P , Pouget A. Probabilistic Interpretation of Population Codes. Neural Computation 1998;10(2):403– 430

    work page 1998

  52. [52]

    Statistically Optimal Perception and Learning: From Behavior to Neural Repre- sentations

    Fiser J, Berkes P , Orbán G, Lengyel M. Statistically Optimal Perception and Learning: From Behavior to Neural Repre- sentations. T rends in cognitive sciences 2010 Mar;14(3):119–30

    work page 2010

  53. [53]

    Probabilistic Brains: Knowns and Unknowns

    Pouget A, Beck JM, Ma WJ, Latham PE. Probabilistic Brains: Knowns and Unknowns. Nature Neuroscience 2013;16(9):1170–1178

    work page 2013

  54. [54]

    Psychosemantics: The Problem of Meaning in the Philosophy of Mind

    Fodor JA. Psychosemantics: The Problem of Meaning in the Philosophy of Mind. The MIT Press; 1987

    work page 1987

  55. [55]

    Knowledge & the Flow of Information

    Dretske FI. Knowledge & the Flow of Information. 4. print ed. A Bradford Book, Cambridge, Mass: MIT Pr; 1986

    work page 1986

  56. [56]

    Language, Thought, and Other Biological Categories: New Foundations for Realism

    Millikan RG. Language, Thought, and Other Biological Categories: New Foundations for Realism. MIT Press; 1987

    work page 1987

  57. [57]

    Knowledge in Perspective: Selected Essays in Epistemology

    Sosa E. Knowledge in Perspective: Selected Essays in Epistemology. Cambridge University Press; 1991

    work page 1991

  58. [58]

    Virtues of the Mind: An Inquiry into the Nature of Virtue and the Ethical Foundations of Knowledge

    Zagzebski LT. Virtues of the Mind: An Inquiry into the Nature of Virtue and the Ethical Foundations of Knowledge. Cambridge University Press; 1996

    work page 1996

  59. [59]

    towards Reconstruction in Epistemology

    Susan H, William D, Evidence and Inquiry. towards Reconstruction in Epistemology. Oxford: Blackwell Publishers; 1993

    work page 1993

  60. [60]

    How Does the Brain Solve Visual Object Recognition? Neuron 2012;73(3):415–434

    DiCarlo JJ, Zoccolan D, Rust NC. How Does the Brain Solve Visual Object Recognition? Neuron 2012;73(3):415–434

    work page 2012

  61. [61]

    Explicit Information for Category-Orthogonal Object Properties Increases along the Ventral Stream

    Hong H, Y amins DLK, Majaj NJ, DiCarlo JJ. Explicit Information for Category-Orthogonal Object Properties Increases along the Ventral Stream. Nature Neuroscience 2016;19(4)

    work page 2016

  62. [62]

    Memory Capacity of Linear vs

    Poirazi P , Mel B. Memory Capacity of Linear vs. Nonlinear Models of Dendritic Integration. In: Advances in Neural Information Processing Systems, vol. 12 MIT Press; 1999

    work page 1999

  63. [63]

    Normalization as a Canonical Neural Computation

    Carandini M, Heeger DJ. Normalization as a Canonical Neural Computation. Nature Reviews Neuroscience 2012;13:51–62

    work page 2012

  64. [64]

    Conjectures Regarding the Nonlinear Geometry of Visual Neurons

    Golden JR, Vilankar KP , Wu MCK, Field DJ. Conjectures Regarding the Nonlinear Geometry of Visual Neurons. Vision Research 2016 Mar;120:74–92. 28 Baker, Lange, Richmond et al

    work page 2016

  65. [65]

    Are Dendrites Conceptually Useful? Neuroscience 2022

    Larkum ME. Are Dendrites Conceptually Useful? Neuroscience 2022

    work page 2022

  66. [66]

    Soft Matching Distance: A Metric on Neural Representations That Captures Single-Neuron T uning

    Khosla M, Williams AH. Soft Matching Distance: A Metric on Neural Representations That Captures Single-Neuron T uning. In: Proceedings of UniReps: The First Workshop on Unifying Representations in Neural Models PMLR; 2024. p. 326–341

    work page 2024

  67. [67]

    Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies

    Achille A, Eccles T, Matthey L, Burgess CP , Watters N, Lerchner A, et al. Life-Long Disentangled Representation Learning with Cross-Domain Latent Homologies. Advances in Neural Information Processing Systems 2018;2018- Decem(Mdl):9873–9883

    work page 2018

  68. [68]

    A Sober Look at the Unsupervised Learning of Disen- tangled Representations and Their Evaluation

    Locatello F, Bauer S, Lucic M, Rätsch G, Gelly S, Schölkopf B, et al. A Sober Look at the Unsupervised Learning of Disen- tangled Representations and Their Evaluation. The Journal of Machine Learning Research 2020 Jan;21(1):209:8629– 209:8690

    work page 2020

  69. [69]

    Are Disentangled Representations Helpful for Abstract Visual Reasoning? Advances in Neural Information Processing Systems 2019;32(NeurIPS)

    van Steenkiste S, Locatello F, Schmidhuber J, Bachem O. Are Disentangled Representations Helpful for Abstract Visual Reasoning? Advances in Neural Information Processing Systems 2019;32(NeurIPS)

    work page 2019

  70. [70]

    The Role of Disentanglement in Generalization

    Montero ML, Ludwig CJ, Costa RP , Malhotra G, Bowers J. The Role of Disentanglement in Generalization. ICLR 2021

    work page 2021

  71. [71]

    arXiv; 2024

    Lippl S, Stachenfeld K, When Does Compositional Structure Yield Compositional Generalization? A Kernel Theory. arXiv; 2024

    work page 2024

  72. [72]

    arXiv; 2023

    Hyvarinen A, Khemakhem I, Morioka H, Nonlinear Independent Component Analysis for Principled Disentanglement in Unsupervised Deep Learning. arXiv; 2023

    work page 2023

  73. [73]

    T oward Causal Representation Learning

    Scholkopf B, Locatello F, Bauer S, Ke NR, Kalchbrenner N, Goyal A, et al. T oward Causal Representation Learning. Proceedings of the IEEE 2021;109(5):612–634

    work page 2021

  74. [74]

    Learning Optimal Representations with the Decodable Information Bottle- neck

    Dubois Y, Kiela D, Vedantam R, Schwab DJ. Learning Optimal Representations with the Decodable Information Bottle- neck. arXiv 2020

    work page 2020

  75. [75]

    Harvard University Press; 1975

    Fodor J, The Language of Thought. Harvard University Press; 1975

    work page 1975

  76. [76]

    The Language of Thought Hypothesis

    Aydede M. The Language of Thought Hypothesis. In: Zalta E, editor. Stanford Encyclopedia of Philosophy; 2010

    work page 2010

  77. [77]

    The Best Game in T own: The Re-emergence of the Language of Thought Hypothesis across the Cognitive Sciences

    Quilty-Dunn J, Porot N, Mandelbaum E. The Best Game in T own: The Re-emergence of the Language of Thought Hypothesis across the Cognitive Sciences. Behavioral and Brain Sciences 2022 Dec;p. 1–55

    work page 2022

  78. [78]

    The Medium and the Message in Mental Imagery: A Theory

    Kosslyn SM. The Medium and the Message in Mental Imagery: A Theory. Psychological Review 1981;88(1):46–66

    work page 1981

  79. [79]

    Mental Rotation of Three-Dimensional Objects

    Shepard RN, Metzler J. Mental Rotation of Three-Dimensional Objects. Science 1971;171(972):701–703

    work page 1971

  80. [80]

    Iconic Representation: Maps, Pictures, and Perception

    Burge T. Iconic Representation: Maps, Pictures, and Perception. In: Wuppuluri S, Doria FA, editors. The Map and the T erritory Cham: Springer International Publishing; 2018.p. 79–100

    work page 2018

Showing first 80 references.