mlsanityData to 14 Oct 2026

Cycle is All You Need: More Is Different

arXiv 2509.21340 ↗First posted 15 Sep 2025cs.NE cs.AI cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

We propose an information-topological framework in which cycle closure is the fundamental mechanism of memory and consciousness. Memory is not a static store but the ability to re-enter latent cycles in neural state space, with invariant cycles serving as carriers of meaning by filtering order-specific noise and preserving what persists across contexts. The dot-cycle dichotomy captures this: transient dots scaffold exploration, while nontrivial cycles encode low-entropy content invariants that stabilize memory. Biologically, polychronous neural groups realize 1-cycles through delay-locked spiking reinforced by STDP, nested within theta-gamma rhythms that enforce boundary cancellation. These micro-cycles compose hierarchically, extending navigation loops into general memory and cognition. The perception-action cycle introduces high-order invariance: closure holds even across sense-act alternations, generalizing ancestral homing behavior. Sheaf-cosheaf duality formalizes this process: sheaves glue perceptual fragments into global sections, cosheaves decompose global plans into actions and closure aligns top-down predictions with bottom-up cycles. Consciousness then arises as the persistence of high-order invariants that integrate (unity) yet differentiate (richness) across contexts. We conclude that cycle is all you need: persistent invariants enable generalization in non-ergodic environments with long-term coherence at minimal energetic cost.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 81 references that are in the map. First posted on arXiv 15 Sep 2025.

Builds on

14 of 81 references.

References · 14

  1. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  2. 2021Attractor and integrator networks in the braincited by 61
  3. 2018Cognitive computational neurosciencecited by 43
  4. 2025Sheaf theory: from deep geometry to deep learningcited by 10
  5. 2022Internal feedback in the cortical perception-action loop enables fast and accurate behaviorcited by 4
  6. 2019Nonmodular architectures of cognitive systems based on active inferencecited by 2
  7. 2024Inverted Inference and Recursive Bootstrapping: A Primal-Dual Theory of Structured Cognitioncited by 2
  8. 2025Self-orthogonalizing attractor neural networks emerging from the free energy principlecited by 2
  9. 2020Poincare return maps in neural dynamics: three examplescited by 1
  10. 2023Computation, Condensation, and the Incompleteness Between Them: A Coupled Foundation of Intelligencecited by 1
  11. 2023On Broken Symmetry in Cognitioncited by 1
  12. 2025Associative Memory for Non-Stationary Environments: A Self-Sizing Generalization of Hopfield Networkscited by 1
2 more
  1. 2025What should we forget? A computational model of memory consolidationcited by 1
  2. 2025The Urysohn Machine: A Metric-Topological Model of Computationcited by 1

Built on by

Not cited yet.