arXiv (All)
open access
Multi-Head Self Attention is a Parameter Identification Mechanism
We prove that a multi-head scaled dot product attention can be viewed as a parameter identification strategy. The ratio of unidentified parameters to the total number of parameters scales like the reciprocal of the number of heads ($1/2 \to 1/(2H)$), meaning models with more heads are structurally m
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
- Evaluating Artificial Models of Cognition#753600
- The influence of placeholders and target stimuli shape on the manifestation of the automatic attentional effect#289531
- The Mirage of Calibrated Confidence: Trajectory-Independence of Verbalized Confidence in Vision-Language Models#1012638
- SCALE: Self-uncertainty Conditioned Adaptive Looking and Execution for Vision-Language-Action Models#684348
- The Modeler-Schema Theory of Consciousness: Diffuse Awareness, Focal Experience, and a Saccadic Consistency Experiment#984940
Record · ID 821187
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