Unverified50% confidenceFactExact time
2014 年 Yosinski 等人在论文《How transferable are features in deep neural networks?》中证明网络浅层学习的特征具有极高通用性，而深层特征逐渐变得任务特定
1
Sources
50%
Confidence
Long-term
Relevance
8/27/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedLow-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.77% 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.72% similarVerifiedDeep learning uses multi-layer neural networks whose structure is inspired by the way neurons in the human brain are connected.71% similarUnverified深度神经网络由输入层、若干隐藏层、输出层构成，每个神经元对前一层输入做加权求和加偏置后通过激活函数做非线性变换70% similarUnverifiedTelgarsky等人的工作证明，深度网络在表示某些函数时比等宽度的浅层网络具有指数级的参数效率优势70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/810175API
curl https://kongchang.com/api/v1/knowledge/claims/810175MCP
get_claim(id=810175)