arXiv · 1910.07617
Path homologies of deep feedforward networks
Abstract
We provide a characterization of two types of directed homology for fully-connected, feedforward neural network architectures. These exact characterizations of the directed homology structure of a neural network architecture are the first of their kind. We show that the directed flag homology of deep networks reduces to computing the simplicial homology of the underlying undirected graph, which is explicitly given by Euler characteristic computations. We also show that the path homology of these networks is non-trivial in higher dimensions and depends on the number and size of the layers within the network. These results provide a foundation for investigating homological differences between neural network architectures and their realized structure as implied by their parameters.
Explore related subjects
Keep this discovery
Samir Chowdhury, Thomas Gebhart, Steve Huntsman, Matvey Yutin. 2019-10-16. Path homologies of deep feedforward networks. https://doi.org/10.1109/icmla.2019.00181
Cite the original work for its findings. Save a collection to share your selection of sources.