Unverified50% confidenceFactExact time
神经正切核（NTK）由Jacot、Gabriel与Hongler在2018年的NeurIPS论文中正式提出
1
Sources
50%
Confidence
Long-term
Relevance
7/12/2026
First Seen
Sources
The Theory of Deep Learning: Why Do Neural Networks Work? A Complete Overview of Theoretical Research
hackernewshackernews7/11/2026
Related Claims
UnverifiedAnthropic published a paper on superposition in 2022, revealing the phenomenon of individual neurons simultaneously encoding multiple concepts.58% similarUnverifiedThe Neural ODE paper published by Chen et al. at NeurIPS in 2018 formally established the connection between backpropagation and the adjoint method55% similarUnverifiedAnthropic's interpretability research team is one of the world's leading research teams, dedicated to understanding how information is represented and processed inside neural networks54% similarVerifiedThe NeurIPS 2019 conference introduced a reproducibility checklist requiring authors to provide code and experimental details.53% similarUnverifiedKarpathy于2015年发表博客文章《递归神经网络的非凡有效性》53% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/494297API
curl https://kongchang.com/api/v1/knowledge/claims/494297MCP
get_claim(id=494297)