MoNet

2000년 도입 · 논문 25편에서 사용

Mixture model network (MoNet) is a general framework allowing to design convolutional deep architectures on non-Euclidean domains such as graphs and manifolds. Image and description from: Geometric deep learning on graphs and manifolds using mixture model CNNs

출처: Geometric deep learning on graphs and manifolds using mixture model CNNs

소개 논문: Geometric deep learning on graphs and manifolds using mixture model CNNs