Unverified50% confidenceFactExact time
2020年的GShard论文提出了辅助损失函数来惩罚不均衡的路由分配
1
Sources
50%
Confidence
Long-term
Relevance
8/25/2026
First Seen
Sources
Related Entities
Related Claims
Unverified研究者引入辅助负载均衡损失来惩罚专家负载不均匀分布，DeepSeek系列还引入专家亲和度机制65% similarUnverifiedSanturkar等人2018年的研究指出BN的真正作用可能在于平滑损失曲面而非减少内部协变量偏移64% similarUnverified2018年Wachter等人将反事实解释形式化为可计算的损失函数：最小化特征变化量的同时约束模型输出翻转到期望类别61% similarVerifiedGradient descent iteratively adjusts weights in the opposite direction of the loss function's gradient, causing the prediction error to converge progressively.60% similarUnverifiedFocal Loss was proposed by Kaiming He et al. in the 2017 RetinaNet paper to address the problem of extreme foreground-background sample imbalance in object detection.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/798219API
curl https://kongchang.com/api/v1/knowledge/claims/798219MCP
get_claim(id=798219)