[KongchangAI]
Unverified50% confidenceFactExact time

Training adopts a masked training strategy: when there are multiple PMUs, the input of one of them is randomly masked while its contribution to the loss is retained, forcing the network to learn to infer the global state from partial measurements.

1
Sources
50%
Confidence
Long-term
Relevance
11/10/2026
First Seen

Sources

Related Entities

Related Claims

Cite This Claim

Stable URI
https://kongchang.com/claim/1153652
API
curl https://kongchang.com/api/v1/knowledge/claims/1153652
MCP
get_claim(id=1153652)