Verified65% confidenceFactExact time
Low-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.
3
Sources
65%
Confidence
Long-term
Relevance
8/12/2026
First Seen
Sources
Related Claims
UnverifiedThe 'depth' in deep learning refers to a network containing multiple hidden layers.80% similarUnverifiedSPLADE and DeepImpact are representatives of learned sparse retrieval, producing sparse vectors whose per-term weights are learned by a neural network and enabling term expansion.79% similarUnverified2014 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77% similarUnverifiedDeep learning excels at pattern recognition but is weak in interpretable logical reasoning, while pure symbolic systems are transparent yet difficult to scale.76% similarUnverifiedThe root cause of the black-box problem in deep learning models lies in the gap between the feature space and the concept space76% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/733368API
curl https://kongchang.com/api/v1/knowledge/claims/733368MCP
get_claim(id=733368)