1
Interpreting FCDNNs via RG on Exponential Family
用重正化群理论揭示全连接深度神经网络在指数族上的工作机制，为深度学习可解释性提供新视角。
arXiv:2606.00157v1 Announce Type: cross Abstract: We consider establishing the interpretability theory of deep learning through constructing a corresp…