A Topology Layer for Machine Learning
Topology applied to real world data using persistent homology has started to find applications within machine learning, including deep learning. We present a differentiable topology layer that computes persistent homology based on level set filtrations and edge-based filtrations. We present three novel applications: the topological layer can (i) regularize data reconstruction or the weights of machine learning models, (ii) construct a loss on the output of a deep generative network to incorporate topological priors, and (iii) perform topological adversarial attacks on deep networks trained with persistence features. The code (www.github.com/bruel-gabrielsson/TopologyLayer) is publicly available and we hope its availability will facilitate the use of persistent homology in deep learning and other gradient based applications.
Code (3)
Tasks
BIG-bench Machine LearningDeep LearningSimilar Papers 제목 키워드 기반
NeuroFabric: Identifying Ideal Topologies for Training A Priori Sparse Networks
Long training times of deep neural networks are a bottleneck in machine learning research. The major impediment to fast training is the quadratic growth of both memory and compute requirements of dense and convolutional …
Variational Autoencoder based Metamodeling for Multi-Objective Topology Optimization of Electrical Machines
Conventional magneto-static finite element analysis of electrical machine design is time-consuming and computationally expensive. Since each machine topology has a distinct set of parameters, design optimization is commo…
DecoderTopology guaranteed segmentation of the human retina from OCT using convolutional neural networks
Optical coherence tomography (OCT) is a noninvasive imaging modality which can be used to obtain depth images of the retina. The changing layer thicknesses can thus be quantified by analyzing these OCT images, moreover t…
PositionSegmentationNTopo: Mesh-free Topology Optimization using Implicit Neural Representations
Recent advances in implicit neural representations show great promise when it comes to generating numerical solutions to partial differential equations. Compared to conventional alternatives, such representations employ …
Self-Supervised LearningScalable Training of Artificial Neural Networks with Adaptive Sparse Connectivity inspired by Network Science
Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural n…
Sparse Learning