Understanding Neural Network Systems for Image Analysis using Vector Spaces and Inverse Maps
CoRR(2024)
摘要
There is strong interest in developing mathematical methods that can be used
to understand complex neural networks used in image analysis. In this paper, we
introduce techniques from Linear Algebra to model neural network layers as maps
between signal spaces. First, we demonstrate how signal spaces can be used to
visualize weight spaces and convolutional layer kernels. We also demonstrate
how residual vector spaces can be used to further visualize information lost at
each layer. Second, we introduce the concept of invertible networks and an
algorithm for computing input images that yield specific outputs. We
demonstrate our approach on two invertible networks and ResNet18.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要