Metraipolis › archive › dc_4b248fc8b592

Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine — arXiv:2610.19220

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.19220
License (as archived)
CC0-1.0
Archived
2026-10-15T14:15:18.325Z
SHA-256 of the archived text
f3e4ee4c460652e9b23845eccabe50c02a961cc9e21421ddb8b8df45bf284398
Stable URL of this page
https://metraipolis.com/documento/dc_4b248fc8b592

How to cite

Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine — arXiv:2610.19220 — arXiv (en), https://arxiv.org/abs/2610.19220 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4b248fc8b592 (Metraipolis archive dc_4b248fc8b592, sha256 f3e4ee4c460652e9b23845eccabe50c02a961cc9e21421ddb8b8df45bf284398)
BibTeX
@misc{dc4b248fc8b592,
  title = {Riding the Fixed-Point Curve: Image Classification in the Continuous Thought Machine — arXiv:2610.19220},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.19220},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4b248fc8b592; sha256 f3e4ee4c460652e9b23845eccabe50c02a961cc9e21421ddb8b8df45bf284398},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.19220. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The Continuous Thought Machine (CTM) is a recurrent network that attends to inputs and makes predictions based on the synchronization between its neurons. On tasks spanning many domains, it displays emergent thought processes that have not been explained. We report a number of findings about how the CTM classifies images, focusing on ImageNet. Each thinking step is an attracting but strongly non-normal map exhibiting balanced amplification (Murphy and Miller, 2009); while attraction is already present at CTM initialization, training highly promotes non-normality. By Banach's theorem, the neural state has a locally unique attracting fixed point, which moves at every step, and the thought trajectory is the curve these fixed points trace, followed one tick behind. Most of that curve's motion is shared across images, and visible as a previously reported traveling wave of activity across neurons. The attention schedule along the thought is largely generic: shuffling queries across images at every tick costs only 7 percent of classification accuracy, while image-independent increments predict the next query with R^2 = 0.98 (held out). Our results suggest that the CTM has found a single strategy to process all ImageNet images.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Computer Vision and Pattern Recognition (cs.CV); Neural and Evolutionary Computing (cs.NE).
Pagina del lavoro: https://arxiv.org/abs/2610.19220 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-15T13:53:35.545Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).