Feed Entities Podcasts Deep Dives Developers About

[KongchangAI]

Real-time AI knowledge base. Every claim is traceable to its source, with data freshness under 24 hours.

Powered by 240+ first-hand AI sources

Knowledge

Feed
Hot Entities
Podcasts

Developers

CLI
MCP Server
REST API
About

© 2026 KongchangAI. The freshest, most accurate AI knowledge

Unverified50% confidenceFactExact time

AdamW引入权重衰减解耦，Lion基于符号动量且显存更低

1

Sources

50%

Confidence

Long-term

Relevance

7/19/2026

First Seen

Sources

从零手写还是直接用sklearn？ML工程师学习路径完全指南

Related Claims

UnverifiedAdam在RMSProp基础上进一步引入一阶矩（动量），并增加了偏差修正机制62% similar Unverified梯度下降及其变体（Adam、AdaGrad等）本质上是数值优化算法56% similar VerifiedAdam结合了动量法与RMSprop的自适应学习率，对每个参数独立维护一阶和二阶梯度的滑动平均52% similar UnverifiedAdam优化器由Diederik Kingma和Jimmy Ba在2014年提出，需要维护一阶动量和二阶动量两份状态52% similar VerifiedAdam 优化器结合了 Momentum 和 RMSProp 的优点，维护梯度的一阶矩估计和二阶矩估计的指数移动平均51% similar

Cite This Claim

Stable URI

https://kongchang.com/claim/563769

API

curl https://kongchang.com/api/v1/knowledge/claims/563769

MCP

get_claim(id=563769)