Verified65% confidenceFactTime unknown
EfficientNet是Google Brain团队于2019年提出的高效网络，通过复合缩放策略同时优化网络深度、宽度和分辨率
3
Sources
65%
Confidence
Long-term
Relevance
6/1/2026
First Seen
Sources
Related Entities
Related Claims
Unverified第二代AutoML以神经架构搜索为标志，Google的NASNet和EfficientNet出自这一思路65% similarUnverifiedGoogle DeepMind applied reinforcement learning to chip floorplanning in 2019 and published the findings in Nature in 2021, demonstrating that AI can surpass human experts on specific EDA sub-tasks.65% similarUnverifiedThe emergent ability phenomenon was systematically documented by the Google DeepMind research team in 2022.65% similarUnverifiedGoogle Brain团队在2020年发表「神经元胞自动机」研究，使用神经网络学习局部更新规则，使元胞自动机能自组织生长出目标图案并在受损后自我修复63% similarUnverified谷歌同时掌控芯片、操作系统、应用框架（AICORE）和模型四个层次，理论上可实现最深度端到端优化63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/20130API
curl https://kongchang.com/api/v1/knowledge/claims/20130MCP
get_claim(id=20130)