Unverified50% confidenceOpinionExact time
Treating UAT as proof that "deep networks are superior to shallow networks" is a common misconception.
1
Sources
50%
Confidence
Long-term
Relevance
10/22/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedIn "On Calibration of Modern Neural Networks" published at ICML in 2017 by Guo et al., the miscalibration phenomenon was empirically demonstrated at scale for the first time, finding that modern deep networks such as ResNet are worse calibrated than earlier shallow networks.69% similarUnverifiedRecent theoretical research has shown that in over-parameterized deep networks, the quality of most local minima is close to the global optimum, and saddle points are the true obstacle to optimization.68% similarVerifiedLow-level features such as edges and textures learned by the shallow layers of deep learning models exhibit strong domain-agnostic properties, while high-level semantic features encoded by deep layers are more domain-specific.66% similarUnverified2012年AlexNet以8层深度网络在ImageNet分类错误率上比第二名低出近11个百分点63% similarUnverifiedOpponents argue that existing deep learning systems are essentially statistical pattern-matching tools and are far from architectures capable of forming autonomous goals63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1084858API
curl https://kongchang.com/api/v1/knowledge/claims/1084858MCP
get_claim(id=1084858)