Unverified50% confidenceFactExact time
The variance σ²(x) captures a mixture of epistemic uncertainty and aleatoric uncertainty, where the former reflects the model having seen little data and the latter reflects the inherent noise in the data itself.
1
Sources
50%
Confidence
Long-term
Relevance
9/11/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedEpistemic uncertainty stems from insufficient training data and can be reduced by adding more data, while aleatoric uncertainty stems from inherent noise in the data and cannot be eliminated by adding more data.77% similarUnverifiedThe expected error of a supervised learning model on unseen data can be decomposed into three components: bias², variance, and irreducible noise75% similarVerifiedNoise information in the context degrades model reasoning accuracy in a nonlinear manner75% similarVerifiedThe three main causes of hallucinations in large models are training data noise, the probability-first mechanism, and insufficient data timeliness.73% similarUnverifiedBatch normalization layers have highly noisy statistical estimates in small-batch scenarios, and combined with the region-level computation characteristics of Dice loss, this amplifies fluctuations in the predicted probability distribution.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/901107API
curl https://kongchang.com/api/v1/knowledge/claims/901107MCP
get_claim(id=901107)