Unverified50% confidenceFactExact time
2012年Hinton团队的AlexNet以top-5错误率从26%骤降至15%的成绩震惊学界
1
Sources
50%
Confidence
Long-term
Relevance
7/14/2026
First Seen
Sources
疟疾细胞AI识别：医学影像分类实践全解析
Related Claims
Unverified2012年Hinton团队的AlexNet以top-5错误率从26%降至15%的成绩，ResNet（2015，微软研究院）通过残差连接解决深层网络梯度消失问题，EfficientNet（2019，Google Brain）通过复合缩放系数优化网络79% similarUnverified2012年ImageNet竞赛中CNN架构将错误率从26%降至15%64% similarUnverifiedThe DeepSuite benchmark has a false positive rate of 44.9% and a false negative rate of 1.2%.63% similarUnverifiedIn 2012, Hinton's team won the ImageNet competition using GPU + ReLU + Dropout, reducing the image classification error rate from 26% to 15%.63% similarUnverified4 basic rules can reduce the AI programming error rate from 41% to 11%61% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/504118API
curl https://kongchang.com/api/v1/knowledge/claims/504118MCP
get_claim(id=504118)