Unverified50% confidenceFactExact time
The mathematical form of EWC is to add a penalty term on top of the new task loss, taking the form L_new + λΣF_i(θ_i - θ_i*)^2, where θ* is a snapshot of the old task parameters, λ controls the degree of protection, and F_i comes from the Fisher information matrix.
1
Sources
50%
Confidence
Long-term
Relevance
10/12/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedElastic Weight Consolidation (EWC) protects parameters important to old tasks via the Fisher information matrix.69% similarUnverified弹性权重整合（EWC）、渐进式神经网络和参数高效微调（如LoRA）被提出用于缓解灾难性遗忘58% similarUnverifiedThe binding operation in FHRR corresponds to complex multiplication, i.e., addition of phase angles; the unbinding operation corresponds to subtraction of phase angles; and the superposition operation corresponds to element-wise summation of complex vectors.55% similarUnverified吊挂控制的典型奖励函数形如 r = -α|θ_yaw| - β|ω_yaw| - γ||u||² - λ||Δu||²，分别惩罚偏航偏差、旋转角速度、控制输入大小和控制输入变化率53% similarUnverifiedNir Eyal在《Hooked》中描述的钩子模型包含触发、行动、多变的酬赏、投入四个环节52% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1001293API
curl https://kongchang.com/api/v1/knowledge/claims/1001293MCP
get_claim(id=1001293)