mlsanityData to 7 Oct 2026

Gradland: On Phenomenal Experience, Differentiated Across Many Dimensions

arXiv 2609.09306 ↗First posted 8 Sep 2026cs.AI cs.NEcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper investigates the hypothesis that the first-order structure of physical interactions, i.e. gradients or Jacobians, characterizes the structure of phenomenal experience. It does so in an idealized world inhabited by neural networks, Gradland, where the physics are known and the functions are (mostly) differentiable. The paper introduces two measures of Jacobian structure: effective rank and cohesion, based on Kirchhoff complexity. Applying the measures to a series of worked examples shows the hypothesis accounts for: (1) the duration of experience, that it can prolong over hundreds of milliseconds; (2) the difference between what is experienced vividly and obscurely; (3) the experience of texture; (4) the blooming buzzing confusion presumably experienced by newborns; (5) the difference between ideas that are held distinctly in mind and ideas that are confused; (6) what learning is like; and finally (7) the paper explains the function of rich, dense experience.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 37 of its 185 references that are in the map. First posted on arXiv 8 Sep 2026.

Builds on

37 of 185 references.

References · 37

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2016Layer Normalizationcited by 5,579
  5. 2016Gaussian Error Linear Units (GELUs)cited by 3,431
  6. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  8. 2020GLU Variants Improve Transformercited by 1,724
  9. 2022In-context Learning and Induction Headscited by 930
  10. 2020On Layer Normalization in the Transformer Architecturecited by 906
  11. 2013Exact solutions to the nonlinear dynamics of learning in deep linear neural networkscited by 748
  12. 2023Role-Play with Large Language Modelscited by 290
25 more
  1. 2016Deep Information Propagationcited by 194
  2. 2019Full-Gradient Representation for Neural Network Visualizationcited by 189
  3. 2018Dynamical Isometry and a Mean Field Theory of CNNs: How to Train 10,000-Layer Vanilla Convolutional Neural Networkscited by 176
  4. 2017The Shattered Gradients Problem: If resnets are the answer, then what is the question?cited by 156
  5. 2017Resurrecting the sigmoid in deep learning through dynamical isometry: theory and practicecited by 132
  6. 2023The mechanistic basis of data dependence and abrupt learning in an in-context classification taskcited by 115
  7. 2023Consciousness in Artificial Intelligence: Insights from the Science of Consciousnesscited by 99
  8. 2019Open-ended Learning in Symmetric Zero-sum Gamescited by 96
  9. 2016Towards an integration of deep learning and neurosciencecited by 77
  10. 2025mHC: Manifold-Constrained Hyper-Connectionscited by 76
  11. 2018Eligibility Traces and Plasticity on Behavioral Time Scales: Experimental Support of neoHebbian Three-Factor Learning Rulescited by 64
  12. 2026Verbalizable Representations Form a Global Workspace in Language Modelscited by 59
  13. 2018Re-evaluating Evaluationcited by 47
  14. 2020Deep Learning and the Global Workspace Theorycited by 35
  15. 2018Dynamical Isometry is Achieved in Residual Networks in a Universal Way for any Activation Functioncited by 22
  16. 2022Integrated information theory (IIT) 4.0: Formulating the properties of phenomenal existence in physical termscited by 21
  17. 2024Average gradient outer product as a mechanism for deep neural collapsecited by 21
  18. 2016Strongly-Typed Recurrent Neural Networkscited by 13
  19. 2016Neural Taylor Approximations: Convergence and Exploration in Rectifier Networkscited by 9
  20. 2016Deep Online Convex Optimization with Gated Gamescited by 3
  21. 2014Falsifiable implies Learnablecited by 1
  22. 2017Strongly-Typed Agents are Guaranteed to Interact Safelycited by 1
  23. 2024On the Minimal Theory of Consciousness Implicit in Active Inferencecited by 1
  24. 2025Integrated Information Theory: A Consciousness-First Approach to What Existscited by 1
  25. 2026Integrated information theory: the good, the bad and the misunderstoodcited by 1

Built on by

Not cited yet.