Expired50% confidenceFactExact time
Researchers use graph neural networks (GNN) to learn neutronics simulations of breeding blankets, enabling sub-second prediction of TBR values for arbitrary combinations of geometric parameters with prediction errors controlled within 1%.
1
Sources
50%
Confidence
Medium-term (~90 days)
Relevance
7/8/2026
First Seen
Valid until: 10/6/2026(expired)
Sources
量子计算+AI超算如何破解核聚变燃料困境
hackernewshackernews7/6/2026
Related Claims
Verified模型量化是将神经网络权重从高精度浮点数压缩为低精度整数的技术73% similarUnverifiedThe core idea of PINN is to simultaneously include data fitting error and physical equation residuals in the neural network loss function, computing partial derivatives of outputs with respect to input coordinates via automatic differentiation.70% similarUnverifiedSPLADE 是一种学习型稀疏检索模型，通过神经网络为文档生成稀疏向量表示，可在倒排索引上高效运行69% similarUnverifiedGNoME基于图神经网络（GNN），通过学习Materials Project等密度泛函理论（DFT）数据库中已知晶体结构稳定性规律进行预测69% similarUnverified大模型中的参数在数学上是神经网络每条连接边上的权重数值和偏置值，训练前随机初始化，通过反向传播算法和梯度下降不断调整68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/236685API
curl https://kongchang.com/api/v1/knowledge/claims/236685MCP
get_claim(id=236685)