arXiv (All)
open access
Near-Floor Geometry Is Generic: Leverage Dispersion in Trained Overcomplete Codes
An overcomplete code packs $F$ features into $d<F$ dimensions, so linear readout of one feature picks up cross-talk from the others, bounded below by the rank-trace floor $W(F,d)=(F-d)/(d(F-1))$. Proximity to this floor is read as evidence of an efficient arrangement. It is not: an i.i.d. code of th
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
This document is indexed with metadata only: full text is not available in the archive for this record. Open the official source ↗
Related documents
- On Why Meta-d′ May Not Go the Distance: Confidence Distance as a Calibration-Based Measure of Metacognition#236857
- Sensorimotor theory, cognitive access and the ‘absolute’ explanatory gap#749368
- Limitation, Totality, and Structural Utility: A Field-Test Analysis of the Architecture of Limitation Against the Cognitive-Theoretic Model of the Universe (CTMU)#118334
- Effectiveness of Video-Based or Written Pelvic Floor Education in Postpartum Women#867435
- Contrasting cognitive control in the Simon and spatial Stroop tasks regarding their interference with the control of standing balance#273316
Record · ID 973156
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive