Unverified50% confidenceFactExact time
Tensor Field Networks (TFN) are a class of general equivariant graph neural networks proposed in 2018, which use spherical harmonic expansions to represent features, making the network strictly equivariant to SO(3) rotations.
1
Sources
50%
Confidence
Long-term
Relevance
10/9/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTFN（Tensor Field Networks）、SEGNN和EquiFold等模型将原子视为图节点，用球谐函数编码原子间方向信息，确保预测不依赖输入坐标系67% similarUnverifiedThe default mode network (DMN) includes brain regions such as the medial prefrontal cortex, posterior cingulate cortex, and angular gyrus; creative thinking requires dynamic switching and coordination between the DMN and the executive control network (the dual-process model of creative cognition).61% similarUnverified原型网络（Prototypical Networks）由 Snell 等人于 2017 年提出，为每个类别维护一个原型向量并通过与原型的距离进行分类61% similarUnverifiedGraph neural network architectures such as GraphSAGE and GAT have demonstrated capabilities in scenarios including social network analysis and molecular property prediction.61% similarUnverifiedThe phenomenon that optimization of over-parameterized neural networks easily converges to good solutions can be explained by Neural Tangent Kernel theory60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/990610API
curl https://kongchang.com/api/v1/knowledge/claims/990610MCP
get_claim(id=990610)